© 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. 128338
    Prev
    Next
    INDEX
    Explanations

    the neuron activates on numeric tokens (numbers and numeric figures) in the text.

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

    first to

    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
     peinado
    -1.16
     umożli
    -1.12
     márm
    -1.09
    đe
    -1.06
    Pengertian
    -1.05
    fatta
    -1.05
     huile
    -1.05
     dió
    -1.04
     zapato
    -1.04
    我们
    -1.03
    POSITIVE LOGITS
     to
    3.03
     in
    1.21
     who
    1.20
     people
    1.15
     with
    1.14
     veiks
    1.10
     españoles
    1.09
     of
    1.07
     кто
    1.06
     ľudí
    1.06
    Activations Density 0.042%

    No Known Activations