© 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. 61985
    Prev
    Next
    INDEX
    Explanations

    Napoleon Bonaparte and his era

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

    Napoleon's reign and empire

    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
    딥
    0.50
    枨
    0.47
    ビル
    0.46
    基督
    0.45
    бах
    0.44
    Wells
    0.44
    懒
    0.43
     پوائن
    0.43
    馔
    0.42
    鸰
    0.41
    POSITIVE LOGITS
     Napoleon
    0.98
    Napoleon
    0.88
     Napole
    0.85
     Bonaparte
    0.70
     France
    0.60
     French
    0.59
    Nap
    0.59
    France
    0.54
     Parisian
    0.54
     nap
    0.53
    Activations Density 0.010%

    No Known Activations