© 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. 22643
    Prev
    Next
    INDEX
    Explanations

    menu item

    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
    mRNA
    0.41
    луб
    0.40
     నిర్వహ
    0.39
    commutative
    0.38
     обши
    0.38
     commutative
    0.38
    㠻
    0.38
    ழிவு
    0.38
    収納
    0.37
    ܂
    0.36
    POSITIVE LOGITS
     item
    0.54
     items
    0.38
    项
    0.37
    item
    0.37
    MenuItem
    0.36
     codes
    0.36
     tile
    0.36
     Proposition
    0.35
     bots
    0.35
    id
    0.35
    Activations Density 0.001%

    No Known Activations