© 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. 22-GEMMASCOPE-RES-131K
    7. 71796
    Prev
    Next
    INDEX
    Explanations

    web automation tools

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

    The neuron activates on mentions of web automation or scraping/testing tool names (e.g. Selenium, Puppeteer, Mechanize, WebDriver, etc.).

    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
     there
    -1.04
     boden
    -1.02
     contributions
    -0.96
     we
    -0.96
    🔙
    -0.93
     infatti
    -0.93
     innovations
    -0.92
     soal
    -0.89
     additions
    -0.87
     hè
    -0.87
    POSITIVE LOGITS
    openqa
    1.13
    obenz
    1.13
    ͗
    1.01
    selenium
    1.01
     Selenium
    0.98
     Venezuelan
    0.97
    stalline
    0.93
     introducido
    0.92
     során
    0.91
     wyś
    0.91
    Activations Density 0.084%

    No Known Activations