© 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. 898
    Prev
    Next
    INDEX
    Explanations

    food and meals

    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
     unem
    0.35
    颉
    0.34
    り返
    0.34
     Verhalten
    0.33
    巅
    0.33
    әү
    0.33
     arxiv
    0.32
     elucidated
    0.32
     [§
    0.31
    缰
    0.31
    POSITIVE LOGITS
     meals
    1.94
     foods
    1.67
     meal
    1.66
     food
    1.65
     comida
    1.59
     makanan
    1.59
    meals
    1.57
     yemek
    1.57
    Meals
    1.55
     cuisine
    1.55
    Activations Density 0.097%

    No Known Activations