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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12364
    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
    ;
    -1.28
     "
    -1.25
     “
    -1.18
    Alright
    -0.98
    NRAS
    -0.97
    торе
    -0.93
     أيام
    -0.91
    Искәрмәләр
    -0.91
     anschließend
    -0.89
     welchen
    -0.88
    POSITIVE LOGITS
     basically
    1.11
    importanza
    1.09
    際には
    1.06
     also
    1.02
     дуже
    1.00
     berbasis
    1.00
    ائع
    1.00
    が起こ
    0.98
     кроссовки
    0.97
     superficies
    0.95
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.