© 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-3-1B
    3. 17-GEMMASCOPE-2-RES-16K
    4. 748
    Prev
    Next
    INDEX
    Explanations

    disclaimer:

    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
     TikTok
    1.02
     tiktok
    0.86
     onboarding
    0.84
     firefighting
    0.80
    🥵
    0.80
     Auschwitz
    0.80
     camp
    0.80
     Tiktok
    0.78
     lock
    0.77
     Stag
    0.77
    POSITIVE LOGITS
    XML
    1.93
     XML
    1.91
     XHTML
    1.82
     Xml
    1.79
     xml
    1.76
    Xml
    1.71
    xml
    1.68
    <html>
    1.63
    xmlns
    1.63
    <%@
    1.58
    Activations Density 0.401%

    No Known Activations