© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 33697
    Prev
    Next
    INDEX
    Explanations

    selective scattering

    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
    📂
    0.49
     Lernen
    0.48
    getFocusAreas
    0.46
    getImageFolder
    0.44
     LOGGER
    0.43
    يبقى
    0.43
    wrapperEl
    0.43
     gamut
    0.41
     Abschnitt
    0.41
     церкви
    0.41
    POSITIVE LOGITS
     consists
    0.39
    uant
    0.38
    round
    0.37
    side
    0.37
    银
    0.36
    orent
    0.36
    oured
    0.36
    eron
    0.36
    字符串
    0.36
    字段
    0.36
    Activations Density 0.000%

    No Known Activations