© 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. 40-GEMMASCOPE-2-RES-262K
    7. 6695
    Prev
    Next
    INDEX
    Explanations

    ordering food or drinks

    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_40_width_262k_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
    NFT
    0.44
     endogenous
    0.43
     ಪುಸ್ತಕ
    0.40
    ActionResult
    0.38
     secular
    0.38
    Furniture
    0.38
     spheroid
    0.38
    뮐
    0.37
    皤
    0.37
    Machine
    0.37
    POSITIVE LOGITS
     eat
    1.00
     eating
    0.98
    食べ
    0.94
     cravings
    0.93
     eats
    0.93
    食べる
    0.90
     craving
    0.87
     먹
    0.86
     tasting
    0.85
     Eating
    0.85
    Activations Density 0.014%

    No Known Activations