© 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. 84661
    Prev
    Next
    INDEX
    Explanations

    snow

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

    The neuron fires on mentions of snow and snow-related terms (e.g., “snow,” “snowfall,” “snowy”).

    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
    ();
    -1.96
    .”
    -1.93
    o
    -1.91
    G
    -1.80
    ?’
    -1.80
    ar
    -1.80
    cou
    -1.79
    だめ
    -1.78
    🧐
    -1.77
    To
    -1.77
    POSITIVE LOGITS
     profundas
    1.95
     treacherous
    1.91
     temáticas
    1.90
    ísticos
    1.88
     Our
    1.81
     artificiales
    1.77
    <bos>
    1.77
     Now
    1.76
     conocidas
    1.73
    FONTE
    1.70
    Activations Density 0.011%

    No Known Activations