© 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-65K
    7. 48608
    Prev
    Next
    INDEX
    Explanations

    x clip term dot server args

    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_65k_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
    িয়া
    0.40
    MACl
    0.39
    ๔
    0.39
    become
    0.38
    Module
    0.37
    methylsulfanyl
    0.37
    isering
    0.37
    睡觉
    0.36
    end
    0.36
    ೫
    0.36
    POSITIVE LOGITS
    уса
    0.39
    рен
    0.39
    لوان
    0.38
    ائل
    0.38
    نش
    0.38
     fur
    0.38
     humor
    0.38
     xyl
    0.38
    дет
    0.37
    ButtonGroup
    0.37
    Activations Density 0.002%

    No Known Activations