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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 70576
    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
    WERS
    -1.13
    КЕ
    -1.13
    racht
    -1.09
    ому
    -1.07
     mitu
    -1.06
    жур
    -1.03
    lask
    -1.03
    БО
    -1.02
     лак
    -1.02
    Objects
    -1.02
    POSITIVE LOGITS
    當時
    1.16
     fanden
    1.09
    　　[
    1.04
    Bism
    1.03
     vervolgens
    1.02
    rofl
    1.02
     machten
    0.96
    Soporte
    0.94
     at
    0.93
     xách
    0.92
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.