© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11141
    Prev
    Next
    INDEX
    Explanations

    Uint8List mapping solutions

    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_7_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
    」（
    2.95
    」
    2.93
    ＞
    2.77
    ۰۰
    2.70
    」，
    2.69
    єї
    2.68
    ».
    2.68
    Else
    2.67
     '.
    2.63
    »
    2.62
    POSITIVE LOGITS
    #![
    2.86
    ру
    2.83
     asyncHandler
    2.69
    anggap
    2.62
    त्याने
    2.60
    orsement
    2.55
    usky
    2.54
    uve
    2.53
    empt
    2.47
    roweak
    2.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.