© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2703
    Prev
    Next
    INDEX
    Explanations

    Vit-1 Elys-3

    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
    Negative Logits
    ことができる
    1.61
     изучение
    1.60
     kertas
    1.54
     piecewise
    1.48
    ाना
    1.46
     Wenn
    1.44
    Wenn
    1.44
    ⅜
    1.44
    ことになる
    1.43
     Shortcuts
    1.35
    POSITIVE LOGITS
    in
    1.99
    ت
    1.95
    с
    1.90
    ia
    1.73
    д
    1.58
    cadilly
    1.57
    ens
    1.56
    am
    1.56
    ্ড
    1.54
    害者
    1.54
    Activations Density 0.006%

    No Known Activations