© 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. 127858
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on numeric tokens (i.e. sequences of digits).

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

    list of conditions

    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
     their
    -2.08
     all
    -1.89
     from
    -1.85
     by
    -1.66
     so
    -1.65
     both
    -1.65
     not
    -1.64
     an
    -1.59
     new
    -1.55
     in
    -1.54
    POSITIVE LOGITS
    during
    1.57
    derry
    1.48
     Dinas
    1.42
     ส์
    1.41
    ౬
    1.41
     trám
    1.40
    苙
    1.37
     verhind
    1.36
    AGRAM
    1.34
     Украине
    1.31
    Activations Density 0.143%

    No Known Activations