© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33050
    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
    чиком
    -1.11
    rounder
    -1.05
     และ
    -1.04
    aas
    -0.96
    alı
    -0.93
    omato
    -0.92
    Friend
    -0.89
    국
    -0.89
    panning
    -0.88
     Rä
    -0.88
    POSITIVE LOGITS
    Debido
    1.19
     Traditionally
    1.13
    Hilsen
    1.13
     sprawling
    1.12
     élo
    1.07
    Allgemeine
    1.05
     banter
    1.02
     cammin
    1.02
    símbolo
    1.02
    Zitat
    1.00
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.