© 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. 23600
    Prev
    Next
    INDEX
    Explanations

    docking and filling

    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
    卫生
    0.40
    merken
    0.40
    颠
    0.39
    ပြင်
    0.38
    вед
    0.38
    事业
    0.38
    噂
    0.37
    트워크
    0.37
    担
    0.37
    舞台
    0.37
    POSITIVE LOGITS
     syndromes
    0.44
     disorders
    0.43
     ulcers
    0.40
    reux
    0.39
     पक्षों
    0.39
     holomorphic
    0.39
     outbursts
    0.39
     processions
    0.39
     flakes
    0.38
     Kopp
    0.38
    Activations Density 0.000%

    No Known Activations