© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 81584
    Prev
    Next
    INDEX
    Explanations

    Python subprocess module

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

    The neuron activates on code snippets that import or call Python’s subprocess module—that is, references to subprocess usage in the script.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    UniqueId
    -0.71
     aliquot
    -0.70
     phthalate
    -0.67
    Choisissez
    -0.64
     glycerin
    -0.64
     tong
    -0.62
     tribunals
    -0.62
     работают
    -0.62
    mişti
    -0.61
    okia
    -0.61
    POSITIVE LOGITS
     process
    4.34
    Process
    3.75
    process
    3.67
     Process
    3.63
     PROCESS
    3.36
    PROCESS
    3.05
     processes
    3.05
     proceso
    2.89
    过程
    2.80
     Processes
    2.64
    Activations Density 0.050%

    No Known Activations