© 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. 110996
    Prev
    Next
    INDEX
    Explanations

    unicode, hex, and special characters

    np_acts-logits-general · gemini-2.5-flash-lite

    hexadecimal digits in Unicode escape sequences or URL encodings.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     has
    -2.53
     with
    -2.39
     it
    -1.91
     gives
    -1.90
     requires
    -1.87
    罽
    -1.84
     using
    -1.84
     When
    -1.82
     makes
    -1.80
     amusing
    -1.80
    POSITIVE LOGITS
    噤
    2.14
    ↵
    1.88
    </b>
    1.80
    AN
    1.79
    <em>
    1.77
    殽
    1.71
    藐
    1.70
    <i>
    1.70
     effectuer
    1.70
     totalement
    1.65
    Activations Density 0.004%

    No Known Activations