© 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. 67672
    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
     الشاشة
    -1.52
     سينما
    -1.32
     دخترانه
    -1.27
     Voyez
    -1.25
    ließen
    -1.20
    детская
    -1.20
    ẕ
    -1.18
    İstinadlar
    -1.17
    pochette
    -1.15
     sécurisé
    -1.15
    POSITIVE LOGITS
     السياس
    1.19
    暧
    1.16
     правительства
    1.15
     imediatamente
    1.13
    rob
    1.08
    𝗼
    1.07
    .
    1.07
     idag
    1.07
     of
    1.05
     склада
    1.04
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.