© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49135
    Prev
    Next
    INDEX
    Explanations

    function calls with object literals

    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_34/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
     якщо
    -0.93
    คัญ
    -0.93
    ご存知
    -0.91
    Хотя
    -0.90
    already
    -0.89
     NSCoder
    -0.88
    then
    -0.87
    cookieParser
    -0.87
    æs
    -0.85
    今度
    -0.85
    POSITIVE LOGITS
    narod
    0.88
     return
    0.88
     certamen
    0.88
    lamic
    0.83
    asst
    0.82
    return
    0.82
     lack
    0.81
    默认为
    0.81
    時半
    0.80
     jste
    0.80
    Activations Density 0.005%

    No Known Activations