© 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. 10-GEMMASCOPE-RES-131K
    7. 111701
    Prev
    Next
    INDEX
    Explanations

    function declarations

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

    opening parentheses in function declarations or calls, particularly in programming 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
     Anſ
    -2.25
     betere
    -2.09
    蕺
    -1.94
     eenen
    -1.93
    </h3>
    -1.91
     několika
    -1.90
    窶
    -1.87
    renowned
    -1.84
    jaqueta
    -1.79
    휀
    -1.79
    POSITIVE LOGITS
    0
    2.31
    ing
    2.11
    to
    1.84
     f
    1.75
    $
    1.74
     fermés
    1.73
    塒
    1.72
    </strong>
    1.70
    }{
    1.69
    -
    1.67
    Activations Density 0.002%

    No Known Activations