© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 127717
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on non‐word symbols—punctuation marks, code/markup tokens (e.g. “;”, “<”, “-->”), and other non‐alphabetic characters.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    Chapter or section markers

    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
    Negative Logits
    manni
    -0.91
     pondok
    -0.89
    ズル
    -0.89
     Introducción
    -0.88
     Cré
    -0.86
     atap
    -0.84
    temun
    -0.83
    下一篇
    -0.82
     também
    -0.81
    日閲覧
    -0.81
    POSITIVE LOGITS
     and
    1.12
     Third
    0.71
    oria
    0.71
     коды
    0.71
    Rud
    0.71
    XXI
    0.69
     Ich
    0.69
     Division
    0.69
    centrum
    0.69
    共和
    0.68
    Activations Density 0.055%

    No Known Activations