© 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. 100419
    Prev
    Next
    INDEX
    Explanations

    main(args) or main(argc, argv)

    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
    运气
    0.47
     இது
    0.42
    exhaustive
    0.42
    
    0.41
     dunno
    0.41
     опро
    0.40
    indagi
    0.38
     طرز
    0.38
    "]])
    0.38
    椙
    0.38
    POSITIVE LOGITS
     suppressed
    0.39
    }{{
    0.37
     dengan
    0.37
     kami
    0.37
     hivyo
    0.37
     mang
    0.37
    smaller
    0.36
    hés
    0.36
    ={{
    0.36
    ={"
    0.35
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.