© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60441
    Prev
    Next
    INDEX
    Explanations

    import ... from .

    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
    .
    -2.28
     only
    -1.93
    Like
    -1.84
    Only
    -1.80
     allowing
    -1.78
     providing
    -1.77
    ing
    -1.76
     just
    -1.70
     製造
    -1.70
    r
    -1.68
    POSITIVE LOGITS
     tohoto
    1.88
     talleres
    1.84
     cauza
    1.80
     různých
    1.79
     ľudí
    1.79
     alebo
    1.77
     that
    1.75
     этого
    1.73
     niekoľ
    1.73
     velké
    1.71
    Activations Density 0.006%

    No Known Activations