© 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. 22-GEMMASCOPE-2-RES-16K
    7. 2513
    Prev
    Next
    INDEX
    Explanations

    news article dates

    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_22_width_16k_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
    대학교
    0.84
     이용하여
    0.84
     사용하여
    0.81
     preventative
    0.75
     eCommerce
    0.71
    .¹
    0.71
    Util
    0.70
     대하여
    0.70
    යා
    0.68
    സ്
    0.67
    POSITIVE LOGITS
     ___
    0.93
    एपी
    0.84
     jueves
    0.84
     Kremlin
    0.83
     Assn
    0.81
    ോഗ
    0.81
    obbly
    0.81
     цьому
    0.81
     sepd
    0.80
     quiere
    0.79
    Activations Density 0.024%

    No Known Activations