© 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. 39651
    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
     such
    -1.08
     to
    -1.05
     might
    -0.97
     trouve
    -0.96
    --*/
    -0.95
    ∅
    -0.93
    }{*}{
    -0.93
     so
    -0.93
     as
    -0.91
     specific
    -0.91
    POSITIVE LOGITS
    一方面
    1.02
    充满了
    1.01
    Läs
    0.98
     ebenfalls
    0.97
     AVOID
    0.95
    Aquí
    0.93
     BOTH
    0.92
    Hechos
    0.92
    cardname
    0.92
    enregistrement
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.