© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 11935
    Prev
    Next
    INDEX
    Explanations

    Supreme Court decisions

    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
     ۲۰
    2.33
    FromArgb
    2.29
    𝗿
    2.26
    𝘂
    2.25
     tiểu
    2.24
     ٢
    2.23
    新人
    2.23
    期限
    2.21
    ۲
    2.20
    :///
    2.19
    POSITIVE LOGITS
    thood
    2.52
    e
    2.22
     buty
    2.13
    oce
    2.04
     supremac
    2.02
    মাত্র
    1.98
    elser
    1.97
     curvature
    1.95
    indexOf
    1.95
    curl
    1.94
    Activations Density 0.028%

    No Known Activations