© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 49150
    Prev
    Next
    INDEX
    Explanations

    chocolate, candy, snacks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dish
    0.47
    餐廳
    0.46
     Utilities
    0.46
     सब्जियों
    0.45
    aqu
    0.45
     Aqua
    0.45
    }),
    0.45
     Worcester
    0.45
    餐
    0.45
    Aqua
    0.44
    POSITIVE LOGITS
    🍫
    1.17
     chocolate
    1.06
    chocolate
    1.00
     шокола
    0.98
    Chocolate
    0.95
     Chocolate
    0.95
     चॉकलेट
    0.93
     candy
    0.91
     chocolates
    0.91
    巧克力
    0.86
    Activations Density 0.138%

    No Known Activations