© 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-16K
    7. 1550
    Prev
    Next
    INDEX
    Explanations

    prefix "re-" actions and concepts

    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_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
    有意
    3.19
     irre
    3.06
     telenov
    3.05
    ل
    2.92
    ट
    2.71
    v
    2.71
    न
    2.65
     arise
    2.58
     poch
    2.58
    dx
    2.56
    POSITIVE LOGITS
     Rxe
    3.19
    šenje
    2.95
     validInput
    2.95
     inFile
    2.91
     एकदा
    2.86
    σ
    2.82
     ليصل
    2.62
    KeyboardMarkup
    2.62
     fondly
    2.54
    $("#
    2.52
    Activations Density 0.671%

    No Known Activations