© 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. 41-GEMMASCOPE-2-RES-262K
    7. 101766
    Prev
    Next
    INDEX
    Explanations

    riddle

    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_all/layer_41_width_262k_l0_big
    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
     ਇੱਕ
    0.53
    َان
    0.50
     equalization
    0.49
    ঃ
    0.49
     ﺍ
    0.49
     և
    0.48
    Ὑ
    0.47
    𝐑
    0.47
    ﻌ
    0.46
    Similarly
    0.46
    POSITIVE LOGITS
     whatnot
    0.76
     sebagainya
    0.75
     hatta
    0.66
     alrededores
    0.56
     البته
    0.50
     dlatego
    0.50
     surtout
    0.50
     생각을
    0.49
    特别是
    0.47
     даже
    0.46
    Activations Density 0.002%

    No Known Activations