© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 100512
    Prev
    Next
    INDEX
    Explanations

    header files

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

    header file include statements in C/C++ code.

    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
    着一
    -2.02
    着一个
    -1.93
    出了一
    -1.91
     a
    -1.89
    了不少
    -1.86
     einem
    -1.77
    辂
    -1.76
    providedIn
    -1.72
    _
    -1.71
     \
    -1.68
    POSITIVE LOGITS
     that
    3.48
     and
    2.89
    ?");
    1.90
    ”),
    1.67
     :");
    1.66
     errone
    1.66
     pering
    1.64
     giapponese
    1.64
     opel
    1.63
    😫
    1.63
    Activations Density 0.054%

    No Known Activations