© 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. 31-GEMMASCOPE-2-RES-262K
    7. 12953
    Prev
    Next
    INDEX
    Explanations

    Indian food and cultural items

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

    food, clothing, and ayurvedic terms

    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_31_width_262k_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
    辉
    0.64
    贯
    0.62
    权重
    0.60
    历史上
    0.57
    িনবার্গ
    0.57
    法规
    0.56
    骁
    0.56
    历史
    0.55
    纽约
    0.55
    该
    0.55
    POSITIVE LOGITS
     mango
    0.93
     ayurved
    0.91
     mehndi
    0.90
     saree
    0.84
     ghee
    0.82
     kurta
    0.80
     Ayurvedic
    0.80
     masala
    0.80
     Pooja
    0.80
     roti
    0.78
    Activations Density 0.166%

    No Known Activations