© 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. 53-GEMMASCOPE-2-RES-65K
    7. 17990
    Prev
    Next
    INDEX
    Explanations

    royal and related concepts

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

    royal

    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_53_width_65k_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
    newParameter
    0.43
     INPUT
    0.42
    inputs
    0.42
     输入
    0.41
    INPUT
    0.41
     सीमेंट
    0.40
     Input
    0.40
     〢
    0.40
    输入
    0.39
     input
    0.39
    POSITIVE LOGITS
     royal
    4.53
     Royal
    4.50
    Royal
    4.44
     ROYAL
    4.38
    royal
    4.31
     रॉयल
    3.83
     royals
    3.72
    ROY
    3.69
    皇家
    3.61
     Royals
    3.59
    Activations Density 0.194%

    No Known Activations