© 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. 128253
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on numeric tokens (digits and related symbols like “±”) in mathematical expressions.

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

    factors of numbers

    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
     итого
    -1.17
     évé
    -1.05
    СЕ
    -1.05
     hunde
    -1.05
     individuel
    -1.05
    точки
    -1.03
    рано
    -1.00
    HttpPost
    -1.00
    точно
    -0.99
     individuelle
    -0.98
    POSITIVE LOGITS
    は以下の
    0.97
     following
    0.96
    animo
    0.96
     risolvere
    0.96
     numerous
    0.96
     nachher
    0.94
    hubaneswar
    0.93
    延伸閱讀
    0.92
    ذن
    0.91
     various
    0.90
    Activations Density 0.001%

    No Known Activations