© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 18136
    Prev
    Next
    INDEX
    Explanations

    best followed by item

    np_acts-logits-general · gemini-2.5-flash-lite

    best for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    وت
    0.57
    。
    0.52
    وب
    0.48
    橘
    0.47
    对
    0.45
    ۔
    0.44
    澤
    0.44
    ។
    0.44
    Автор
    0.44
    ду
    0.43
    POSITIVE LOGITS
     Dang
    0.40
     Dard
    0.40
     महिन्यात
    0.40
     Sub
    0.39
     Titles
    0.39
     dnev
    0.39
     singolo
    0.39
    sächlich
    0.39
     Erfol
    0.39
    dell
    0.38
    Activations Density 0.013%

    No Known Activations