© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 11776
    Prev
    Next
    INDEX
    Explanations

    provider responsibility tutorials

    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_17_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
     և
    0.73
     في
    0.70
     şi
    0.65
    0.59
     التي
    0.58
    ,
    0.58
     és
    0.57
     અને
    0.56
     (
    0.55
     και
    0.55
    POSITIVE LOGITS
    ಮಾಳಿಗೆ
    0.67
     وړاندوین
    0.64
    𐰣
    0.63
    <unused856>
    0.63
     فونب
    0.61
    𒀜
    0.60
    𐰤
    0.60
    ዢ
    0.59
     Villanova
    0.59
    <unused796>
    0.59
    Activations Density 4.021%

    No Known Activations