© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 27691
    Prev
    Next
    INDEX
    Explanations

    Lua, PS5, AI, Jutland

    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
     mistake
    0.47
     padlock
    0.46
     backsplash
    0.45
     SafeArea
    0.45
    一顆
    0.44
     bijection
    0.43
     समझिए
    0.42
    戰
    0.42
    一颗
    0.42
    मार्
    0.42
    POSITIVE LOGITS
    elijke
    0.50
    ang
    0.48
    unuz
    0.47
     Бе
    0.46
     angin
    0.46
     hende
    0.46
    umber
    0.45
    lijke
    0.45
    ewöhn
    0.44
    Be
    0.43
    Activations Density 0.001%

    No Known Activations