© 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. 10-GEMMASCOPE-RES-131K
    7. 98746
    Prev
    Next
    INDEX
    Explanations

    universal quantifier "all"

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    蛲
    -2.00
    ㈯
    -1.94
    瘊
    -1.91
    但却
    -1.83
    蟊
    -1.81
    狲
    -1.80
    沩
    -1.71
    蒌
    -1.71
     ہے۔
    -1.70
    鸶
    -1.70
    POSITIVE LOGITS
     with
    2.11
     people
    2.03
     you
    1.99
    2
    1.98
    (
    1.97
    There
    1.90
    in
    1.88
    :
    1.84
     this
    1.77
    <em>
    1.73
    Activations Density 0.010%

    No Known Activations