© 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. 64631
    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
     diligently
    -1.70
    ဴ
    -1.64
     venturing
    -1.54
    וֹ
    -1.54
    וּ
    -1.47
    Ꭽ
    -1.45
    cuál
    -1.41
    際には
    -1.41
    tersebut
    -1.41
     this
    -1.41
    POSITIVE LOGITS
    <>
    1.23
     is
    1.23
     kleinere
    1.13
     Resultat
    1.08
     منذ
    1.06
    Love
    1.06
     câbles
    1.06
     melding
    1.04
     serien
    1.03
     vitesses
    1.01
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.