© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8603
    Prev
    Next
    INDEX
    Explanations

    Japanese culture

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

    Japanese places

    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_40_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
     caribbean
    0.55
     Malta
    0.52
     আফ্রিকার
    0.52
    堊
    0.51
    ugoslav
    0.50
     Croatia
    0.50
     चर्च
    0.49
    驃
    0.48
     किंग्स
    0.48
     Valletta
    0.48
    POSITIVE LOGITS
     Japanese
    1.93
    Japanese
    1.88
     япон
    1.84
     japanese
    1.73
    japanese
    1.70
     일본
    1.67
     Japan
    1.66
    Japan
    1.59
     Japon
    1.59
     japonais
    1.58
    Activations Density 0.390%

    No Known Activations