© 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. 31-GEMMASCOPE-2-RES-262K
    7. 8839
    Prev
    Next
    INDEX
    Explanations

    access personalized features

    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_31_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
    ाय
    0.45
    ヒ
    0.44
     sturdy
    0.44
    ्स
    0.43
     prevenir
    0.42
    bmod
    0.41
     अफ्रीका
    0.41
     casos
    0.41
     garantizar
    0.40
    bodyParser
    0.39
    POSITIVE LOGITS
     هناك
    0.47
     الجرس
    0.45
     té
    0.44
     Vlog
    0.44
     計
    0.44
     Mutations
    0.43
     Mutant
    0.43
    <>
    0.43
     Duel
    0.42
     Activities
    0.42
    Activations Density 0.002%

    No Known Activations