© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60940
    Prev
    Next
    INDEX
    Explanations

    paper citations and identifiers

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

    The neuron is sensitive to structural document markers—especially numbers (e.g. section or year numerals) and heading/citation punctuation (slashes, hyphens, periods) that denote sections or references.

    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
    )​
    -0.75
    `;
    -0.69
    avo
    -0.69
     Shard
    -0.68
     DESCRIPT
    -0.65
     Rosario
    -0.65
    cko
    -0.64
    copyWith
    -0.64
     السياسي
    -0.63
    Org
    -0.63
    POSITIVE LOGITS
     promising
    0.79
     legends
    0.77
    fahrens
    0.77
    Ẁ
    0.77
    承诺
    0.75
     parenthood
    0.75
    ForEach
    0.75
    thirty
    0.74
    ルトン
    0.73
     میوه
    0.73
    Activations Density 0.065%

    No Known Activations