© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 47941
    Prev
    Next
    INDEX
    Explanations

    due to or thanks to

    np_acts-logits-general · gemini-2.5-flash-lite

    specific case or example

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    গুলি
    0.50
    h
    0.48
    ing
    0.48
     monographs
    0.46
    im
    0.46
    ES
    0.46
    গুলিকে
    0.46
    SE
    0.45
    axis
    0.45
     advisory
    0.45
    POSITIVE LOGITS
     Valentino
    0.48
    飚
    0.47
     వలన
    0.46
     اندرو
    0.45
    鐢
    0.45
     sayesinde
    0.45
     Afgh
    0.44
     utilizzo
    0.44
    壱
    0.44
     grazie
    0.43
    Activations Density 0.001%

    No Known Activations