© 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. 16939
    Prev
    Next
    INDEX
    Explanations

    ballet and dance companies

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

    ballet

    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
    اندی
    0.47
    
    0.45
     노래
    0.43
     songwriting
    0.41
     xm
    0.41
     infek
    0.41
     şark
    0.40
     proposing
    0.39
     songwriter
    0.39
    🎸
    0.38
    POSITIVE LOGITS
     ballet
    2.00
     Ballet
    1.78
     ballerina
    1.49
    🩰
    1.20
     baller
    1.14
    バレ
    1.08
     danced
    0.81
     pointe
    0.79
     balle
    0.77
     bal
    0.73
    Activations Density 0.026%

    No Known Activations