© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 9715
    Prev
    Next
    INDEX
    Explanations

    configuration files

    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
    జ్య
    1.15
    儡
    1.15
     saker
    1.14
    자
    1.12
    winkel
    1.11
    prim
    1.11
     Delt
    1.06
     সাধন
    1.01
    ән
    1.00
     כן
    1.00
    POSITIVE LOGITS
    ا
    1.70
    اا
    1.58
    t
    1.47
    lcd
    1.37
     algebras
    1.36
    fem
    1.36
     devlet
    1.36
     тыс
    1.35
     pathogenicity
    1.34
     ModelState
    1.32
    Activations Density 0.000%

    No Known Activations