© 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. 17-GEMMASCOPE-2-RES-16K
    7. 15363
    Prev
    Next
    INDEX
    Explanations

    Bundle

    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
    Negative Logits
     switchTo
    2.52
     keyValue
    2.43
     taj
    2.40
    jsonData
    2.34
    nue
    2.31
    もら
    2.30
    نة
    2.19
    ുള്ള
    2.16
     гор
    2.15
    Ꮕ
    2.14
    POSITIVE LOGITS
     fenders
    2.55
    ﺭ
    2.55
    hx
    2.47
    ्य
    2.36
    ب
    2.31
     perceber
    2.24
    考える
    2.23
    bys
    2.22
    링
    2.22
    bilical
    2.21
    Activations Density 0.006%

    No Known Activations