© 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. 34-GEMMASCOPE-RES-131K
    7. 116507
    Prev
    Next
    INDEX
    Explanations

    program execution state

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

    The neuron fires on words that describe program execution events and their ordering (e.g. “called,” “finish,” “before,” “after,” “execution,” “start”).

    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
     défaite
    -0.79
     dzień
    -0.79
    接口
    -0.79
     settimana
    -0.78
    𖧧
    -0.76
     menerapkan
    -0.75
    geschoss
    -0.75
    வே
    -0.75
    ikbaar
    -0.74
    زين
    -0.73
    POSITIVE LOGITS
     execution
    4.28
    execution
    3.23
    Execution
    3.08
     Execution
    3.02
     executing
    2.78
     executed
    2.69
    执行
    2.50
     executions
    2.47
     execute
    2.44
     executes
    2.31
    Activations Density 0.178%

    No Known Activations