© 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. 127802
    Prev
    Next
    INDEX
    Explanations

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

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

    code syntax punctuation

    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
     such
    -1.05
     throwing
    -1.00
    sives
    -0.98
    kontak
    -0.97
    iedades
    -0.97
    得太
    -0.95
    ɫ
    -0.94
     propriedades
    -0.94
    aneamente
    -0.93
     mosca
    -0.93
    POSITIVE LOGITS
     recientemente
    0.93
     piccoli
    0.89
     pantaloni
    0.88
    헷
    0.85
     prácticamente
    0.85
     gruppi
    0.84
     веке
    0.83
     kleinen
    0.83
     récemment
    0.82
     majeurs
    0.82
    Activations Density 0.009%

    No Known Activations