© 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. 67888
    Prev
    Next
    INDEX
    Explanations

    context-based stories and lyrics

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    狰
    -0.94
    scha
    -0.93
    实践
    -0.92
     เว
    -0.91
    currentState
    -0.91
    MECHAN
    -0.89
    Practices
    -0.88
    regelen
    -0.87
    áct
    -0.87
     绿
    -0.87
    POSITIVE LOGITS
     nieco
    0.95
     political
    0.88
     story
    0.86
    Ꮢ
    0.86
    paigns
    0.84
     Customers
    0.83
    ↵↵↵↵↵↵
    0.82
    ↵↵↵↵↵
    0.82
     politics
    0.81
     réflé
    0.81
    Activations Density 0.087%

    No Known Activations