© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71226
    Prev
    Next
    INDEX
    Explanations

    cef, antibiotherapy, FileDialog, addOn

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

    The neuron strongly activates on numeric tokens or symbols representing numbers (e.g. section/figure numbers, numerals, measurement values, and numbering markers).

    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
    There
    -3.11
    Maybe
    -2.81
    That
    -2.77
    What
    -2.67
    You
    -2.67
    Going
    -2.63
    Another
    -2.63
    Now
    -2.61
    Two
    -2.58
    After
    -2.55
    POSITIVE LOGITS
    {
    3.17
    as
    3.13
    냑
    2.78
    料
    2.66
    栳
    2.56
    k
    2.55
     it
    2.50
     anderen
    2.41
    ,.
    2.41
     the
    2.34
    Activations Density 0.003%

    No Known Activations