© 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. 112469
    Prev
    Next
    INDEX
    Explanations

    programming constructs

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

    method names or function calls that convert data to a different format or type.

    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
    巨大的
    -2.63
     ['./
    -2.27
     \
    -2.25
    !)
    -2.22
     vagy
    -2.20
     \\
    -2.20
     وال
    -2.13
    小声
    -2.09
    A
    -2.08
    是他
    -2.06
    POSITIVE LOGITS
    豋
    3.23
    盌
    2.77
    厛
    2.61
    猡
    2.50
    桖
    2.38
    嫫
    2.28
    幛
    2.20
    我可以
    2.20
    カプ
    2.19
    ࿙
    2.17
    Activations Density 0.000%

    No Known Activations