© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 17-GEMMASCOPE-2-RES-16K
    7. 1859
    Prev
    Next
    INDEX
    Explanations

    web technologies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_17_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
     दरभंगा
    1.25
     Burrow
    1.14
     Schroeder
    1.07
    圳
    1.06
     Kac
    1.04
     کیف
    1.03
    霄
    0.98
     Mishra
    0.97
     commuting
    0.96
     சந்திர
    0.96
    POSITIVE LOGITS
     HTML
    2.35
    HTML
    2.30
     html
    2.22
     Html
    2.10
    <html>
    1.97
    Html
    1.95
     XHTML
    1.83
    html
    1.80
    innerHTML
    1.63
    <div>
    1.52
    Activations Density 0.206%

    No Known Activations