© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 4053
    Prev
    Next
    INDEX
    Explanations

    Haitian Creole phrases

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

    Vodou Loa and spirits

    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
     Abhäng
    0.42
    Poi
    0.40
    怯
    0.40
     দেরি
    0.39
     Народ
    0.38
     ঋণ
    0.37
    Weiter
    0.37
    언
    0.37
    Upp
    0.36
    Можно
    0.36
    POSITIVE LOGITS
     yo
    0.60
     lò
    0.55
     mwen
    0.54
     pral
    0.54
     yek
    0.53
     fè
    0.52
     liya
    0.52
     ç
    0.51
     yon
    0.51
     lan
    0.50
    Activations Density 0.001%

    No Known Activations