© 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. 11279
    Prev
    Next
    INDEX
    Explanations

    Arch Linux

    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
    …。
    0.85
    เหล่านี้
    0.84
    ...
    0.81
    に限
    0.77
     convierten
    0.77
    ฯ
    0.75
     especializada
    0.75
    送料無料
    0.71
    …
    0.70
     convierte
    0.69
    POSITIVE LOGITS
    besiege
    1.48
     ominous
    1.35
    <unused1191>
    1.32
    <unused412>
    1.30
     timid
    1.29
    <unused995>
    1.29
    <unused407>
    1.28
     בש
    1.28
    <unused725>
    1.28
    cmml
    1.28
    Activations Density 0.068%

    No Known Activations