© 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. 129291
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on numeric tokens (e.g. numbers or measurements), i.e. it detects numeric values in the text.

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

    list of entities and 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
    Not in Any Lists

    No Comments

    Negative Logits
     ceremonia
    -1.27
     ronde
    -1.09
     Ragnarok
    -1.07
     versi
    -1.06
     fisk
    -1.04
     plafon
    -1.04
     sade
    -1.03
     ondu
    -1.03
     zapatillas
    -1.02
     pittores
    -1.02
    POSITIVE LOGITS
     около
    1.05
     почти
    1.03
     ложки
    0.94
     после
    0.94
     Total
    0.92
     участь
    0.92
    ～！
    0.92
     всех
    0.90
     тис
    0.90
     From
    0.90
    Activations Density 0.014%

    No Known Activations