© 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. 29-GEMMASCOPE-2-RES-16K
    7. 3267
    Prev
    Next
    INDEX
    Explanations

    y7

    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_29_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
    १८६
    0.80
     मंगलवार
    0.79
     dins
    0.74
     Selasa
    0.69
    ঈশ্বর
    0.68
    ানন্দ
    0.66
    <0xAE>
    0.65
     sanded
    0.64
     lành
    0.64
    ś
    0.63
    POSITIVE LOGITS
    7
    3.68
     seven
    3.45
     Seven
    3.32
    ７
    3.21
     ۷
    3.17
    七
    3.15
    ۷
    3.06
    ٧
    3.01
    Seven
    2.99
     seventh
    2.98
    Activations Density 0.762%

    No Known Activations