© 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. 2624
    Prev
    Next
    INDEX
    Explanations

    specialized lightweight ball

    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
    놓
    0.46
    H
    0.44
    書籍
    0.42
    C
    0.42
    κρα
    0.41
    F
    0.41
     fí
    0.40
    o
    0.40
    φορά
    0.38
     perturb
    0.38
    POSITIVE LOGITS
    పే
    0.47
    ApiCalls
    0.46
    پی
    0.45
    くな
    0.45
     nazw
    0.44
     زیب
    0.43
     spettac
    0.43
    ActiveClass
    0.41
    ₂)
    0.41
     intérieur
    0.41
    Activations Density 0.000%

    No Known Activations