© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 100943
    Prev
    Next
    INDEX
    Explanations

    scale up

    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
     الاساس
    0.41
     baking
    0.39
     Marquez
    0.38
     изме
    0.37
     Baking
    0.36
    益
    0.36
    zież
    0.36
    adie
    0.36
     emailing
    0.35
    尽
    0.35
    POSITIVE LOGITS
     up
    0.97
    up
    0.83
     Up
    0.82
    ขึ้น
    0.81
    Up
    0.80
    アップ
    0.79
     вверх
    0.79
     lên
    0.74
     ups
    0.68
    ups
    0.63
    Activations Density 0.000%

    No Known Activations