© 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. 32882
    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
    Not in Any Lists

    No Comments

    Negative Logits
     encourages
    -1.47
     maintains
    -1.44
     enhances
    -1.41
     promotes
    -1.38
     looked
    -1.37
     gives
    -1.34
     removes
    -1.34
     nestled
    -1.33
     allows
    -1.31
     reinforces
    -1.30
    POSITIVE LOGITS
    during
    1.41
    possibly
    1.34
     ludicrous
    1.29
     soooo
    1.29
     скриншот
    1.27
     Dinas
    1.26
    たまに
    1.26
     EARLY
    1.23
    actually
    1.23
     wondrous
    1.23
    Activations Density 0.001%

    No Known Activations