© 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. 10-GEMMASCOPE-RES-131K
    7. 84319
    Prev
    Next
    INDEX
    Explanations

    symbols and code

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

    The neuron fires on standalone punctuation marks (asterisks, slashes, vertical bars, etc.) used as formatting or list‐separator symbols.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    .
    -2.06
     A
    -1.86
     facilitates
    -1.84
     schwierig
    -1.84
     tries
    -1.83
    Almost
    -1.77
     several
    -1.74
    Another
    -1.73
     genellikle
    -1.72
     lavish
    -1.70
    POSITIVE LOGITS
     westfalen
    1.99
    蓐
    1.98
    '
    1.98
     直播
    1.83
    ti
    1.82
     eſſ
    1.81
     baumwolle
    1.75
     礼物
    1.66
    wwww
    1.65
     accessoires
    1.65
    Activations Density 0.031%

    No Known Activations