© 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. 10-GEMMASCOPE-RES-131K
    7. 72
    Prev
    Next
    INDEX
    Explanations

    code, comments, and specific phrases

    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_10/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
     to
    -2.31
    us
    -1.70
    ti
    -1.65
     {
    -1.64
    },
    -1.56
    is
    -1.55
     no
    -1.54
    他也
    -1.52
     \
    -1.49
     —
    -1.48
    POSITIVE LOGITS
    ↵
    1.89
     recientemente
    1.88
    
    1.84
    ть
    1.80
     hauptsächlich
    1.78
     BOTH
    1.73
     aquellas
    1.70
    튿
    1.69
     Jeśli
    1.69
     píše
    1.68
    Activations Density 0.000%

    No Known Activations