© 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. 32658
    Prev
    Next
    INDEX
    Explanations

    exciting features

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

    Without explicit programming

    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
     can
    0.54
    %(
    0.52
     on
    0.49
     Villain
    0.46
     bluff
    0.45
     back
    0.45
     Cabot
    0.45
    trunc
    0.44
     Cronin
    0.44
    binary
    0.43
    POSITIVE LOGITS
    म
    0.54
    खाना
    0.50
    助于
    0.47
    冰箱
    0.47
    用于
    0.47
    इस
    0.47
    供应商
    0.47
     حجم
    0.46
    一部分
    0.46
     расходы
    0.46
    Activations Density 0.000%

    No Known Activations