© 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. 34-GEMMASCOPE-RES-131K
    7. 92922
    Prev
    Next
    INDEX
    Explanations

    live events, sports, and numerical data

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

    The neuron flags non-lexical tokens—punctuation marks, numeric strings, and other formatting symbols (e.g. apostrophes, slashes, years)—rather than ordinary words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    āng
    -0.80
    ViewState
    -0.80
    Imgur
    -0.78
     ومل
    -0.76
     Penalty
    -0.74
     Comprom
    -0.74
    ♒
    -0.73
     livraison
    -0.72
     identité
    -0.72
     još
    -0.71
    POSITIVE LOGITS
     Collider
    0.97
    Collider
    0.94
    COLL
    0.94
    غير
    0.76
     Additionally
    0.76
    ägg
    0.76
    フレット
    0.75
     manufactured
    0.75
    collider
    0.74
     wonderful
    0.74
    Activations Density 0.004%

    No Known Activations