© 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. 81195
    Prev
    Next
    INDEX
    Explanations

    engine start and starter

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

    The neuron activates on occurrences of “start” (and its variants like “starter,” “starting,” “start-up”) often in the context of motors or engines.

    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
    \}=\
    -0.76
    뵙
    -0.74
    stage
    -0.73
    熬
    -0.72
    ステ
    -0.71
    ϊ
    -0.69
    EMENT
    -0.69
     настоящее
    -0.68
    merate
    -0.68
    Expires
    -0.68
    POSITIVE LOGITS
     start
    3.53
     starting
    3.11
     starter
    2.81
     starts
    2.80
    Start
    2.80
    start
    2.72
     started
    2.72
     Start
    2.70
    启动
    2.66
    Starting
    2.63
    Activations Density 0.035%

    No Known Activations