© 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. 11115
    Prev
    Next
    INDEX
    Explanations

    ffmpeg command-line tool

    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
    ક
    1.41
    महा
    1.39
     iba
    1.36
    s
    1.34
    r
    1.32
    fully
    1.30
     poblaciones
    1.30
    suff
    1.28
    ні
    1.26
    ки
    1.23
    POSITIVE LOGITS
     PartialEq
    1.82
    檛
    1.80
    특별시
    1.70
    एं
    1.59
     Electrons
    1.56
    ें
    1.55
     eyesight
    1.51
     UnwrapRef
    1.51
    水分
    1.50
    至於
    1.50
    Activations Density 0.001%

    No Known Activations