© 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. 22-GEMMASCOPE-RES-131K
    7. 66387
    Prev
    Next
    INDEX
    Explanations

    executing queries and commands

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

    This neuron fires on code snippets that invoke or reference external command execution (e.g. shell commands, backticks, `system`/`exec` calls).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     thefts
    -0.90
    {?>
    -0.86
     hakk
    -0.86
     blir
    -0.84
    arResult
    -0.83
    вающие
    -0.83
    arı
    -0.83
    coglie
    -0.82
     is
    -0.82
    DataSnapshot
    -0.81
    POSITIVE LOGITS
    んだから
    1.16
     bubuk
    1.13
     executes
    1.10
     실행
    1.09
     Ranks
    1.08
     monetary
    1.06
    埂
    1.02
     Echin
    1.00
     grabar
    0.99
    Geograf
    0.99
    Activations Density 0.005%

    No Known Activations