© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5975
    Prev
    Next
    INDEX
    Explanations

    royalty and their domains

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

    king or queen

    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
    Negative Logits
     artist
    0.45
     groep
    0.43
     apporter
    0.43
     prepd
    0.43
    lular
    0.42
     opet
    0.41
     contributors
    0.41
     Registered
    0.41
     polype
    0.41
     =$
    0.41
    POSITIVE LOGITS
    陛下
    1.02
    alty
    0.89
     emeritus
    0.87
    🤴
    0.84
     Emeritus
    0.82
    ship
    0.82
     himself
    0.79
    陛
    0.77
    妃
    0.68
    වර
    0.64
    Activations Density 0.079%

    No Known Activations