© 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. 101590
    Prev
    Next
    INDEX
    Explanations

    subprocess, postpartum, prefrontal, nvarchar

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

    references to the Python "subprocess" module.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    是個
    -2.48
    -
    -2.13
    Two
    -2.00
    是很
    -2.00
    でて
    -1.98
    </h4>
    -1.97
     potret
    -1.97
    In
    -1.95
    out
    -1.92
    有點
    -1.92
    POSITIVE LOGITS
    ஂ
    2.83
    飈
    2.75
    餿
    2.59
    妧
    2.50
    癩
    2.45
     mauva
    2.45
    軚
    2.31
    缐
    2.31
    鹛
    2.28
    榦
    2.28
    Activations Density 0.002%

    No Known Activations