© 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. 11772
    Prev
    Next
    INDEX
    Explanations

    Main method

    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
    emiz
    2.46
    ون
    2.46
    ো
    2.38
    imizi
    2.30
    elbe
    2.24
    es
    2.24
    imde
    2.24
    em
    2.23
    ோ
    2.20
    ים
    2.20
    POSITIVE LOGITS
    <bos>
    2.46
     Sep
    2.11
    ୭
    2.05
    mml
    1.99
    হোক
    1.98
    *[
    1.95
    SAP
    1.93
    RouterProvider
    1.91
    榔
    1.90
    ̀
    1.88
    Activations Density 0.020%

    No Known Activations