© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1117
    Prev
    Next
    INDEX
    Explanations

    steroids and conversions

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

    scientific names and chemical formulas of steroid compounds.

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

    The neuron strongly fires on numeric sequences (digits, hyphenated numbers, and Greek‐letter–number combinations) that denote positions or identifiers in chemical and steroid names.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Soils
    -0.83
    czer
    -0.80
     peptides
    -0.80
     thậm
    -0.78
     象
    -0.77
     nối
    -0.77
     Amino
    -0.73
     amputation
    -0.72
    gadier
    -0.72
     Hilbert
    -0.72
    POSITIVE LOGITS
     pregn
    0.82
    Estr
    0.80
     cortisol
    0.79
    sterone
    0.78
     testosterone
    0.75
     Yen
    0.73
    conversions
    0.71
     plankton
    0.70
    /*---
    0.69
    eti
    0.69
    Activations Density 0.166%

    No Known Activations