© 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. 127809
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     like
    -1.47
     of
    -1.30
     not
    -1.25
    kram
    -1.23
     on
    -1.20
     値下げ
    -1.20
     from
    -1.14
     for
    -1.10
     daudz
    -1.10
     in
    -1.09
    POSITIVE LOGITS
    ೩
    1.35
    俨
    1.29
    órica
    1.27
     humeur
    1.23
    羸
    1.23
    嗙
    1.23
     Détails
    1.23
    veillance
    1.22
    durante
    1.22
    ݮ
    1.21
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.