© 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. 98665
    Prev
    Next
    INDEX
    Explanations

    min and max

    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
     and
    -2.88
     with
    -2.73
     to
    -2.09
     as
    -2.00
     on
    -1.93
     not
    -1.70
     only
    -1.67
     just
    -1.65
     at
    -1.57
    Appellants
    -1.56
    POSITIVE LOGITS
     activités
    1.73
    ビックリ
    1.56
     malgré
    1.53
     colgante
    1.43
     itinéraires
    1.43
     orgánico
    1.41
     tp
    1.36
     mę
    1.35
     rédu
    1.34
    combined
    1.33
    Activations Density 0.008%

    No Known Activations