© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 123689
    Prev
    Next
    INDEX
    Explanations

    executing code, scripts, commands

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

    the word "run" in code or command contexts.

    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
    戩
    -2.44
     หลัง
    -2.34
    葙
    -2.25
    gives
    -2.23
     ehemalige
    -2.22
    臵
    -2.22
    asserole
    -2.14
    riculares
    -2.13
    鲀
    -2.13
    give
    -2.05
    POSITIVE LOGITS
    o
    3.20
     was
    3.16
    (
    3.06
    ?"
    2.83
    *
    2.56
    ed
    2.48
    run
    2.45
    塒
    2.42
    ll
    2.34
    y
    2.31
    Activations Density 0.012%

    No Known Activations