© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11927
    Prev
    Next
    INDEX
    Explanations

    webdriver for browsers

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

    The neuron detects decimal or floating-point numeric tokens (numbers with a period and digits).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Kiss
    0.55
     Do
    0.53
     Shelf
    0.53
    Do
    0.52
     chon
    0.52
    繇
    0.52
     Stamford
    0.51
     Cedar
    0.51
    യ്ക്ക്
    0.51
    DOI
    0.50
    POSITIVE LOGITS
     executable
    0.71
     webdriver
    0.63
    executable
    0.61
    🚙
    0.60
     ücretsiz
    0.59
    chromedriver
    0.59
     gratuitement
    0.58
    EXECUT
    0.58
    Drivers
    0.57
    পিন
    0.57
    Activations Density 0.015%

    No Known Activations