© 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. 38634
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
     corsair
    -0.98
     chup
    -0.96
     incendie
    -0.96
     toti
    -0.95
     PSOE
    -0.94
    硨
    -0.94
    泔
    -0.93
     terapi
    -0.93
     Sá
    -0.91
    Taco
    -0.91
    POSITIVE LOGITS
     they
    1.16
     i
    1.09
     [
    1.07
     pretty
    1.04
     ll
    0.98
     sim
    0.96
     act
    0.95
     stets
    0.94
    ound
    0.94
     their
    0.93
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.