© 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. 34-GEMMASCOPE-RES-131K
    7. 58161
    Prev
    Next
    INDEX
    Explanations

    shell commands execution

    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
    avras
    -0.84
    pushd
    -0.84
     samochód
    -0.81
    Louisa
    -0.76
    sieu
    -0.75
    Grim
    -0.74
    gunaan
    -0.74
    yq
    -0.73
    FileUtils
    -0.73
     podle
    -0.73
    POSITIVE LOGITS
    echo
    1.12
     echo
    1.11
     sleep
    0.94
    logger
    0.91
    free
    0.90
     free
    0.88
     clear
    0.85
    clear
    0.83
    sleep
    0.82
    date
    0.80
    Activations Density 0.108%

    No Known Activations