© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130017
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on numeric tokens or numerical data (e.g. measurements, scores, years, or other numbers).

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

    introducing additional points

    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
    ,
    -0.95
     of
    -0.93
     ク
    -0.90
     Entdecken
    -0.86
    所以在
    -0.86
    Finalmente
    -0.85
     аккура
    -0.84
    الد
    -0.83
     finalement
    -0.83
    )=
    -0.81
    POSITIVE LOGITS
     also
    4.25
     также
    3.38
    Also
    3.22
     inoltre
    3.00
     Also
    3.00
     همچنین
    2.91
    Также
    2.86
     außerdem
    2.80
     επίσης
    2.69
     Также
    2.67
    Activations Density 0.087%

    No Known Activations