© 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. 191558
    Prev
    Next
    INDEX
    Explanations

    audience lists and targeting

    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
     क्वेश्च
    0.41
     MDR
    0.40
    ╁
    0.38
     procès
    0.38
    
    0.38
     lParam
    0.38
     নির্ভরশীল
    0.37
     பட்டம்
    0.37
     walmart
    0.36
    䀎
    0.36
    POSITIVE LOGITS
    List
    0.86
     List
    0.73
     list
    0.66
    list
    0.64
     lists
    0.58
    リスト
    0.56
     Lists
    0.56
     सूची
    0.55
     список
    0.54
     Liste
    0.54
    Activations Density 0.006%

    No Known Activations