© 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. 68834
    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
    ttää
    -0.98
    囮
    -0.96
     its
    -0.93
    ització
    -0.93
     eğiti
    -0.91
    ificato
    -0.91
    OTER
    -0.91
     anuncia
    -0.90
     Fils
    -0.90
    ژگی
    -0.89
    POSITIVE LOGITS
     diminished
    1.19
    ૩
    0.99
     demonstrated
    0.98
     standardized
    0.98
     inadequate
    0.98
     too
    0.97
     enfri
    0.97
    增加了
    0.97
     decât
    0.96
     garanzia
    0.95
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.