© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 127847
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on numeric literals (tokens consisting of digits) in code.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    programming language keywords and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ꨄ
    -0.88
     Virol
    -0.88
    graphics
    -0.87
    ออกมา
    -0.85
    дино
    -0.84
     celebración
    -0.83
    Biblia
    -0.82
     květ
    -0.82
    grä
    -0.81
     stát
    -0.79
    POSITIVE LOGITS
     compliment
    0.78
    uggets
    0.77
     keinem
    0.73
    Fantastic
    0.71
    laquo
    0.71
     steigen
    0.71
    某些
    0.70
    Schwe
    0.69
    早餐
    0.69
    apkamer
    0.69
    Activations Density 0.011%

    No Known Activations