© 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. 38323
    Prev
    Next
    INDEX
    Explanations

    web driver waits

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

    This neuron fires on mentions of programming‐oriented keywords and technology names (e.g. “Using,” “Java,” “Selenium,” “WebDriver,” exceptions) in code-question contexts.

    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
    틀
    -0.96
    Action
    -0.79
    Level
    -0.77
    Responder
    -0.75
     Fee
    -0.74
    fein
    -0.73
    Levi
    -0.73
    感受
    -0.71
    flat
    -0.70
     پاسخ
    -0.69
    POSITIVE LOGITS
     wait
    1.70
    wait
    1.44
    Wait
    1.38
     Wait
    1.37
     waited
    1.30
     waits
    1.28
     WebDriverWait
    1.21
     waiting
    1.20
     WAIT
    1.15
    waits
    1.15
    Activations Density 0.007%

    No Known Activations