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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 91073
    Prev
    Next
    INDEX
    Explanations

    castration and hormones

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

    medical and scientific terms related to steroid hormones and castration in scientific research papers.

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

    The neuron strongly activates on numeric tokens and scientific numeric measurements (e.g. counts, units, years, and parenthesized data), indicating it’s detecting numbers and quantitative data.

    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
    🤰
    -0.71
     DISTRIBUTION
    -0.71
     herpes
    -0.69
    STUDENT
    -0.67
     Foam
    -0.67
     Diploma
    -0.67
    bail
    -0.67
    mortar
    -0.67
     obtient
    -0.67
     bott
    -0.66
    POSITIVE LOGITS
     eun
    1.80
     Eun
    1.49
    Eun
    1.47
    eun
    1.42
     emas
    1.20
     testosterone
    1.20
     cast
    1.13
     androgen
    1.09
     arom
    1.05
     hormonal
    1.03
    Activations Density 0.161%

    No Known Activations