© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 6940
    Prev
    Next
    INDEX
    Explanations

    running python scripts in tutorials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    öst
    1.22
     cắt
    1.19
     taşı
    1.17
     bask
    1.15
    诉
    1.14
    kö
    1.14
     internes
    1.13
    SRS
    1.13
     rojos
    1.13
     mouvement
    1.12
    POSITIVE LOGITS
    (((
    1.72
    ваш
    1.62
    商品説明
    1.59
     radiometric
    1.59
    ろん
    1.52
     (((
    1.48
    anyaan
    1.48
     quadrature
    1.47
    ちは
    1.46
    <bos>
    1.46
    Activations Density 0.017%

    No Known Activations