© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 2493
    Prev
    Next
    INDEX
    Explanations

    section numbering and lettering

    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
    Not in Any Lists

    No Comments

    Negative Logits
    )*((
    1.15
     tweet
    1.14
    )=[
    1.10
    ),[
    1.08
     tweeted
    0.99
     MJ
    0.99
     upgraded
    0.99
    )=(\
    0.97
     pooch
    0.97
     outlet
    0.97
    POSITIVE LOGITS
    Acknowledgments
    2.30
    Preface
    2.25
    Acknowledgements
    2.24
    Acknowledg
    2.20
     Acknowledg
    2.19
    Contributors
    2.17
    はじめ
    2.15
     CONTRIBUTORS
    2.12
    序
    2.03
    ACKNOWLEDGMENTS
    2.03
    Activations Density 0.026%

    No Known Activations