© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 54465
    Prev
    Next
    INDEX
    Explanations

    Shenandoah, Sherbrooke

    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
    ibility
    0.43
    笑了
    0.41
     LOC
    0.40
    lename
    0.40
    Ꮬ
    0.39
    actic
    0.39
    LOC
    0.38
    BLEND
    0.38
    enic
    0.38
    auce
    0.38
    POSITIVE LOGITS
     બનાવવા
    0.54
     नुक
    0.43
     թվ
    0.41
    нон
    0.39
    んな
    0.37
     Equitable
    0.36
     랜
    0.36
    дили
    0.35
    વવા
    0.35
     trench
    0.35
    Activations Density 0.003%

    No Known Activations