© 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. 22-GEMMASCOPE-RES-131K
    7. 129357
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric tokens or digit‐based identifiers (e.g. numbers, indices, numeric constants).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    code delimiters

    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
    Not in Any Lists

    No Comments

    Negative Logits
    cio
    -0.74
    kuper
    -0.73
     cũ
    -0.73
    ogast
    -0.70
    育て
    -0.69
    vely
    -0.69
     enterprises
    -0.69
    peł
    -0.68
     sovi
    -0.68
    zies
    -0.68
    POSITIVE LOGITS
     Asimismo
    0.87
    ราช
    0.87
    govina
    0.81
    ímica
    0.79
     ANYTHING
    0.78
    Nhap
    0.78
    製作
    0.78
     полиции
    0.76
    こちらも
    0.76
     ícones
    0.75
    Activations Density 0.024%

    No Known Activations