© 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. 11318
    Prev
    Next
    INDEX
    Explanations

    describing recent changes

    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
    ivní
    2.19
     traité
    2.05
    ႈ
    2.03
    ist
    2.02
     Gur
    1.97
     договору
    1.96
     matières
    1.95
     poche
    1.95
    按照
    1.94
    [{{
    1.92
    POSITIVE LOGITS
    та
    3.05
    ت
    2.78
    ы
    2.59
    en
    2.58
    㿟
    2.47
    etku
    2.46
    vori
    2.46
    messer
    2.45
    ла
    2.44
    pretty
    2.38
    Activations Density 0.023%

    No Known Activations