© 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. 42678
    Prev
    Next
    INDEX
    Explanations

    royal court and titles

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

    royal and political intrigue

    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
     backpacking
    0.57
     hiker
    0.50
    রির
    0.48
     backpack
    0.47
     renta
    0.47
    獾
    0.47
     backpacks
    0.46
     экспер
    0.46
     теркә
    0.46
     теркәлү
    0.45
    POSITIVE LOGITS
     palace
    1.00
     palaces
    0.86
     Palace
    0.85
     royal
    0.79
    宫
    0.75
    朕
    0.75
     coronation
    0.75
    宮
    0.71
    陛下
    0.70
    皇帝
    0.69
    Activations Density 0.039%

    No Known Activations