© 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. 13952
    Prev
    Next
    INDEX
    Explanations

    solve for variables

    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
    <bos>
    -2.03
    。”
    -2.03
    ☫
    -1.95
    葙
    -1.93
    檠
    -1.89
    This
    -1.88
    ！】
    -1.80
     ไม่
    -1.79
    ⚋
    -1.77
    횃
    -1.70
    POSITIVE LOGITS
    .
    2.30
     only
    2.13
     same
    2.03
     from
    1.93
     first
    1.91
     every
    1.87
     EVERY
    1.80
     ALL
    1.80
     most
    1.70
     after
    1.69
    Activations Density 0.036%

    No Known Activations