© 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. 11113
    Prev
    Next
    INDEX
    Explanations

    well, best, option

    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
     oatmeal
    1.37
    ים
    1.32
    ю
    1.30
     notas
    1.23
     prev
    1.21
     së
    1.17
     bitte
    1.17
     lipoprotein
    1.16
    ました
    1.14
    зова
    1.13
    POSITIVE LOGITS
    t
    1.95
    tım
    1.59
    tura
    1.58
    től
    1.55
    ت
    1.43
    ek
    1.43
    kör
    1.41
    tch
    1.37
    ﻲ
    1.37
    ছে
    1.34
    Activations Density 0.000%

    No Known Activations