© 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. 12582
    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
     blusa
    -1.48
     Pří
    -1.38
     bordado
    -1.37
    Ẩ
    -1.36
     coloridas
    -1.35
    produksi
    -1.34
     Drž
    -1.33
     Dě
    -1.33
    AÇÃO
    -1.33
     réus
    -1.33
    POSITIVE LOGITS
    ar
    1.85
    T
    1.84
    M
    1.83
    u
    1.80
    L
    1.79
    P
    1.77
    A
    1.74
    B
    1.73
    k
    1.70
    G
    1.70
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.