© 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. 236556
    Prev
    Next
    INDEX
    Explanations

    dates and places

    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
     開始
    0.49
     două
    0.48
     সম্পূর্ণরূপে
    0.47
    完整的
    0.47
    وسی
    0.45
    ياء
    0.44
    手表
    0.44
    蔥
    0.44
    鼕
    0.44
    owels
    0.43
    POSITIVE LOGITS
     Ryan
    0.51
     cunning
    0.49
    l
    0.47
     prowess
    0.46
     virtuous
    0.46
    estar
    0.45
     Arsenal
    0.45
     assassin
    0.44
     stark
    0.44
     Diana
    0.44
    Activations Density 0.001%

    No Known Activations