© 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. 112156
    Prev
    Next
    INDEX
    Explanations

    programming method calls

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

    method calls that create, initialize, or execute objects in programming code, particularly builder patterns and method invocations with parentheses.

    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
    
    -1.93
     predominantly
    -1.73
    ⩥
    -1.72
     renowned
    -1.69
     unveils
    -1.66
     obtiene
    -1.66
    铊
    -1.65
     BECAUSE
    -1.63
    樒
    -1.63
     alluring
    -1.56
    POSITIVE LOGITS
    <
    2.03
    !
    2.02
    {
    1.94
    </
    1.80
    There
    1.70
    Since
    1.66
    ;
    1.64
     that
    1.61
    With
    1.59
     has
    1.56
    Activations Density 0.003%

    No Known Activations