© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 272
    Prev
    Next
    INDEX
    Explanations

    questions starting with what is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_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
     propagates
    0.91
     exact
    0.85
    ez
    0.85
    forall
    0.78
     +
    0.78
     degrades
    0.78
     trap
    0.77
     tub
    0.76
     /
    0.76
     fails
    0.75
    POSITIVE LOGITS
     Capítulo
    1.84
     Einführung
    1.72
    Chapter
    1.70
     romanzo
    1.64
    Acknowledgments
    1.63
     Bibliothèque
    1.63
    Preface
    1.62
    CHAPTER
    1.62
     Chương
    1.59
    Introduction
    1.59
    Activations Density 0.045%

    No Known Activations