© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48943
    Prev
    Next
    INDEX
    Explanations

    execution

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

    The neuron detects mentions of executions or execution-related terms (e.g. “execution,” “executed,” “executioner”).

    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
    ურ
    -0.81
     Homeless
    -0.75
    fras
    -0.74
    Assault
    -0.74
     Wurzel
    -0.74
    יתי
    -0.74
     противополо
    -0.73
    jątk
    -0.73
     Dzięki
    -0.73
    ybė
    -0.71
    POSITIVE LOGITS
     execution
    4.16
     executions
    3.38
     executed
    3.23
     Execution
    3.22
    execution
    3.13
    Execution
    3.08
     execute
    2.84
     executes
    2.66
     executing
    2.66
     EXEC
    2.64
    Activations Density 0.042%

    No Known Activations