© 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. 32
    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
     virke
    -1.41
     funktioner
    -1.24
    endpush
    -1.14
     område
    -1.14
     varme
    -1.13
     нарушение
    -1.12
     gyvento
    -1.12
     samti
    -1.11
     banderas
    -1.09
     trå
    -1.06
    POSITIVE LOGITS
     &
    1.08
     cintura
    1.02
     mesmer
    1.02
     surround
    0.96
    turkish
    0.94
     zatím
    0.93
    husky
    0.93
    lowns
    0.92
     cubierto
    0.92
     الفلسط
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.