© 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. 223375
    Prev
    Next
    INDEX
    Explanations

    restaurants and shopping

    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
    قتل
    0.46
    柩
    0.44
     employment
    0.42
     brutality
    0.42
    瞿
    0.40
     FBI
    0.40
    徒歩
    0.39
     Alaskan
    0.38
     martyrdom
    0.38
    غي
    0.37
    POSITIVE LOGITS
    Shopping
    0.49
    Restaurants
    0.48
    restaurants
    0.47
    餐厅
    0.46
    凳
    0.44
     Shopping
    0.44
    shopping
    0.43
    Wool
    0.43
     restaurantes
    0.42
     午
    0.42
    Activations Density 0.001%

    No Known Activations