© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 11417
    Prev
    Next
    INDEX
    Explanations

    won't disappoint

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_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
    an
    2.92
    र
    2.75
    ان
    2.71
    ни
    2.51
    ../
    2.39
    ו
    2.34
    oare
    2.30
     presion
    2.27
    o
    2.27
    是他
    2.24
    POSITIVE LOGITS
    Также
    2.49
     IntPtr
    2.13
     gái
    2.07
    ያንዳ
    2.05
    Explicit
    2.05
    ㅠ
    2.00
    ल
    1.97
     discretized
    1.95
    Đây
    1.95
     exquisitely
    1.92
    Activations Density 0.004%

    No Known Activations