© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11419
    Prev
    Next
    INDEX
    Explanations

    list operations, list creation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    8
    -2.06
    9
    -2.06
    3
    -1.96
    6
    -1.91
    4
    -1.81
    [
    -1.70
    
    -1.70
    攢
    -1.66
     два
    -1.62
     charmant
    -1.61
    POSITIVE LOGITS
      
    1.69
    谵
    1.56
    replyreport
    1.55
    ेमाल
    1.54
     картинка
    1.53
     semua
    1.50
     or
    1.50
     ваша
    1.48
    你喜欢
    1.48
    lijker
    1.47
    Activations Density 0.005%

    No Known Activations