© 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. 26962
    Prev
    Next
    INDEX
    Explanations

    CAN-BUS capabilities

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on tokens that are numeric values (digit sequences, including integers, decimals, and measurements).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     vœux
    -1.94
     anún
    -1.93
     épisodes
    -1.85
     Sekret
    -1.84
    ⎔
    -1.82
     itinéraires
    -1.81
     icônes
    -1.81
    EEEEEEEE
    -1.78
     victoires
    -1.78
     objectifs
    -1.77
    POSITIVE LOGITS
     not
    2.23
     or
    2.20
     where
    1.96
     what
    1.95
     now
    1.88
     which
    1.83
     and
    1.82
     including
    1.74
     that
    1.73
     in
    1.70
    Activations Density 0.045%

    No Known Activations