© 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. 40-GEMMASCOPE-2-RES-262K
    7. 1713
    Prev
    Next
    INDEX
    Explanations

    quantifier or delimiter

    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/layer_40_width_262k_l0_medium
    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
    нары
    0.50
    ం
    0.48
    ัง
    0.46
    ంత్ర
    0.46
    員
    0.45
    文書
    0.45
    窺
    0.45
     CMOS
    0.44
    庫
    0.43
     syringe
    0.42
    POSITIVE LOGITS
    thus
    0.52
    updates
    0.50
    monia
    0.50
    KNOWN
    0.49
    시키는
    0.49
    sortBy
    0.48
    ępuje
    0.48
    neighborhood
    0.47
     අව
    0.47
     මො
    0.46
    Activations Density 0.000%

    No Known Activations