© 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. 44979
    Prev
    Next
    INDEX
    Explanations

    acronyms and initialisms

    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
    pertino
    -1.84
    imetry
    -1.78
    lawayo
    -1.77
    ścioła
    -1.77
    [];
    -1.76
    hasiswa
    -1.73
    周泽
    -1.73
    aternion
    -1.72
    thique
    -1.70
    迁移
    -1.70
    POSITIVE LOGITS
    </b>
    2.23
    0
    1.99
    *
    1.80
     Hingga
    1.71
     Untuk
    1.70
     '
    1.69
    1
    1.68
    <
    1.63
    8
    1.61
     Kemudian
    1.59
    Activations Density 0.111%

    No Known Activations