© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 7508
    Prev
    Next
    INDEX
    Explanations

    type CREATED IDENT

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    𐰀
    0.45
    㮍
    0.44
    وزیشن
    0.42
    泹
    0.41
    หมือน
    0.40
    羵
    0.40
     datth
    0.40
    🍠
    0.39
    <unused726>
    0.39
    ปลี่ยน
    0.39
    POSITIVE LOGITS
    to
    0.40
    markt
    0.36
    [
    0.36
     to
    0.36
    bf
    0.35
    Rates
    0.35
     Guru
    0.35
    g
    0.34
     Type
    0.34
    Type
    0.33
    Activations Density 0.000%

    No Known Activations