© 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. 22-GEMMASCOPE-RES-131K
    7. 64294
    Prev
    Next
    INDEX
    Explanations

    MEDIA STATEMENT

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     such
    -1.08
     probably
    -1.02
     because
    -1.01
     perhaps
    -1.00
     такі
    -0.95
     maybe
    -0.93
     with
    -0.90
     for
    -0.90
     about
    -0.88
     кіль
    -0.88
    POSITIVE LOGITS
    腟
    1.10
     különböző
    1.09
    zdě
    1.06
    ariate
    1.05
    éraire
    1.05
    跸
    1.05
    嗫
    1.05
     roze
    1.02
     zí
    1.00
     dient
    0.99
    Activations Density 0.001%

    No Known Activations