© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72690
    Prev
    Next
    INDEX
    Explanations

    regional measure

    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
     the
    -2.44
     will
    -2.13
     in
    -1.98
     should
    -1.84
     can
    -1.84
     for
    -1.83
    Because
    -1.80
    This
    -1.77
     because
    -1.73
    They
    -1.62
    POSITIVE LOGITS
    を使用した
    2.11
    <bos>
    2.11
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.92
     verwendeten
    1.92
     dispuesto
    1.89
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.87
     distancias
    1.86
    jenige
    1.85
    棡
    1.83
    ":"+
    1.81
    Activations Density 0.083%

    No Known Activations