© 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. 13-GEMMASCOPE-2-RES-16K
    7. 13884
    Prev
    Next
    INDEX
    Explanations

    code variable declarations and loops

    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_13_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
     洗
    2.06
    <unused416>
    1.90
     Scully
    1.88
     Essays
    1.86
    喝酒
    1.84
     歴史
    1.84
    拡散方程式
    1.83
    <unused1089>
    1.82
    <unused972>
    1.82
    <unused1631>
    1.82
    POSITIVE LOGITS
    i
    1.50
    <b>
    1.49
    r
    1.25
    <strong>
    1.23
    ers
    1.15
    эр
    1.14
    ер
    1.07
    y
    1.01
    ر
    1.01
     therefor
    0.99
    Activations Density 0.001%

    No Known Activations