© 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. 22826
    Prev
    Next
    INDEX
    Explanations

    action verbs

    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
     salonu
    -2.30
    鷽
    -2.27
     faciliter
    -2.27
     ludicrous
    -2.23
     participer
    -2.22
    蹓
    -2.22
     plafon
    -2.19
     apprécier
    -2.16
    鵙
    -2.14
    癭
    -2.14
    POSITIVE LOGITS
     by
    3.03
     at
    3.00
     for
    2.91
     as
    2.89
     in
    2.83
     on
    2.77
     without
    2.72
     because
    2.66
     of
    2.63
     an
    2.56
    Activations Density 0.019%

    No Known Activations