© 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. 129254
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on numeric tokens, especially standalone numbers or floats (e.g. line numbers and other numeric values).

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

    script, Q, Elizabeth, Nebraska, Study

    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
     keramik
    -1.26
     关于
    -1.21
     meren
    -1.07
     Meksi
    -1.06
     Kerajaan
    -1.05
     istan
    -1.02
     kaos
    -1.02
    newtheorem
    -0.98
     kela
    -0.96
     kompleks
    -0.95
    POSITIVE LOGITS
     otherwise
    0.93
     currant
    0.90
     Ziegler
    0.89
    יך
    0.89
     Otherwise
    0.88
    を進
    0.87
    zeitig
    0.84
     reemplazo
    0.84
    見る
    0.83
     レシピ
    0.83
    Activations Density 0.000%

    No Known Activations