© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100522
    Prev
    Next
    INDEX
    Explanations

    gonadotropins and stimulating hormone

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron identifies hormones and endocrine terminology, particularly focusing on gonadotropins and reproductive hormones.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    hormones and endocrine-related terms, particularly gonadotropins and reproductive hormones.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron identifies hormones and related terms from reproductive and endocrine systems, particularly gonadotropins and related compounds.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    hormone and endocrine-related terminology, particularly focusing on gonadotropins and reproductive hormones.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly responds to mentions of gonadotropin‐type hormones (e.g. HCG, GnRH, LH, FSH) and their subunits.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    龊
    -1.81
    𓆜
    -1.76
    .~\
    -1.74
    逦
    -1.72
    Pcs
    -1.70
     "..
    -1.64
    ᠌
    -1.55
    
    -1.55
    ༷
    -1.52
    ྄
    -1.52
    POSITIVE LOGITS
    ↵↵
    2.20
     as
    1.82
     by
    1.67
     on
    1.48
     et
    1.40
     time
    1.38
     at
    1.37
     lontano
    1.37
     without
    1.36
     NEVER
    1.30
    Activations Density 0.098%

    No Known Activations