© 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. 113232
    Prev
    Next
    INDEX
    Explanations

    evaluating code execution

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

    programming-related terms, especially those related to code interpretation, evaluation, and execution.

    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
     who
    -1.31
     about
    -1.30
     but
    -1.30
     SDLK
    -1.29
    ⊂
    -1.28
    t
    -1.24
     de
    -1.23
     dalla
    -1.19
    ̵
    -1.19
     Vögel
    -1.16
    POSITIVE LOGITS
    FORMANCE
    1.24
    挲
    1.20
     ॥
    1.16
    ʁ
    1.14
    ၞ
    1.13
    さてさて
    1.12
    ầ
    1.12
    歌词
    1.12
     Tribute
    1.09
    金沢
    1.09
    Activations Density 0.091%

    No Known Activations