© 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-3-27B-IT
    3. 41-GEMMASCOPE-2-RES-262K
    4. 30591
    Prev
    Next
    INDEX
    Explanations

    mention specific detail

    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
    這位
    0.44
     złot
    0.42
     указыва
    0.41
     phy
    0.41
    EnumType
    0.41
    ://${
    0.40
    <unused706>
    0.40
    :"+
    0.40
    chris
    0.40
    ('${
    0.40
    POSITIVE LOGITS
     ____
    0.46
    …,
    0.45
    ...).
    0.43
    ...,
    0.42
    /
    0.41
    做到
    0.41
    ___
    0.41
     ________
    0.40
    ________
    0.39
     [
    0.39
    Activations Density 0.003%

    No Known Activations