© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 10253
    Prev
    Next
    INDEX
    Explanations

    go-, followed by project names

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

    the hyphen or dash character when it appears in programming contexts, particularly in Go language code, URLs, and technical file paths.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    you
    -2.78
    which
    -2.53
    that
    -2.53
     untuk
    -2.27
    for
    -2.20
    when
    -2.17
    i
    -2.08
    </b>
    -2.02
    what
    -2.00
     поэтому
    -1.97
    POSITIVE LOGITS
    ↵
    2.67
    ";
    2.11
    淶
    1.97
    𖣘
    1.93
     legions
    1.92
    떳
    1.91
     terá
    1.88
    ꯳
    1.87
    Dieu
    1.86
    ITALY
    1.86
    Activations Density 0.030%

    No Known Activations