© 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. 10-GEMMASCOPE-RES-131K
    7. 1197
    Prev
    Next
    INDEX
    Explanations

    Chauvet Cave, Cauchy, Chalmers, swine, Dalhousie

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

    names related to mathematics and academic figures, particularly recognizing terms like "Chauvet," "Cauchy," and other proper names in scholarly contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    桕
    -2.97
    re
    -2.84
    );
    -2.80
    !”
    -2.75
    栳
    -2.41
    鰾
    -2.38
     it
    -2.33
     ‘
    -2.31
    但她
    -2.25
     航空
    -2.25
    POSITIVE LOGITS
    棪
    2.73
    ?
    2.20
    哎呀
    2.20
    哏
    2.19
     "
    2.14
     плана
    2.08
     оба
    2.08
    吔
    2.06
    沨
    2.06
    ції
    2.03
    Activations Density 0.007%

    No Known Activations