© 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. 45569
    Prev
    Next
    INDEX
    Explanations

    pronouns he she his her

    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
     for
    -2.56
     with
    -2.42
     of
    -2.42
     to
    -2.33
     this
    -2.30
     from
    -2.27
     in
    -2.25
     by
    -2.14
     when
    -2.13
     as
    -2.06
    POSITIVE LOGITS
     hemd
    1.93
     ‚
    1.93
     zwi
    1.77
     zout
    1.77
     bezw
    1.71
     ww
    1.68
     gitar
    1.64
    拄
    1.63
    2
    1.63
     cuchar
    1.63
    Activations Density 0.093%

    No Known Activations