© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14306
    Prev
    Next
    INDEX
    Explanations

    royal titles and residences

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

    royal family and monarchy

    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_16k_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
     recklessly
    0.50
    Xc
    0.47
     aggressively
    0.45
    Ninja
    0.45
     Bayou
    0.45
    👺
    0.45
    ≐
    0.45
     ninja
    0.44
     minimax
    0.44
    👹
    0.44
    POSITIVE LOGITS
     royal
    0.91
     monarchy
    0.84
     royals
    0.80
    royal
    0.76
     Royal
    0.75
     monarch
    0.75
     королев
    0.75
     Buckingham
    0.73
    皇家
    0.73
    陛下
    0.70
    Activations Density 0.112%

    No Known Activations