© 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-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 15482
    Prev
    Next
    INDEX
    Explanations

    www

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
     $[-
    0.68
    번에
    0.59
    $[
    0.57
     জায়গায়
    0.54
     проє
    0.54
    ிட்ட
    0.52
     $[
    0.52
    헤
    0.52
    ̲
    0.52
    ෙකු
    0.51
    POSITIVE LOGITS
     www
    4.72
    www
    4.47
     WWW
    3.23
    WWW
    3.20
    wwww
    2.80
     ww
    2.45
    ww
    2.13
     http
    1.49
     WW
    1.48
    WW
    1.38
    Activations Density 0.120%

    No Known Activations