© 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. 31-GEMMASCOPE-2-RES-65K
    7. 63738
    Prev
    Next
    INDEX
    Explanations

    main function with args

    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_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
     طرز
    0.38
    Следу
    0.38
    ต
    0.38
     จัก
    0.37
     использу
    0.37
    뀝
    0.36
    stract
    0.36
    otage
    0.36
    数
    0.35
    อะ
    0.35
    POSITIVE LOGITS
     ফ্র
    0.42
    ={"
    0.40
     plt
    0.38
     сезона
    0.37
     Mart
    0.37
     Martins
    0.37
     kabel
    0.37
     возможностей
    0.37
     kami
    0.36
    ({"
    0.36
    Activations Density 0.001%

    No Known Activations