© 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. 34-GEMMASCOPE-RES-131K
    7. 118989
    Prev
    Next
    INDEX
    Explanations

    swift programming constructs

    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_34/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
    DispatchQueue
    -1.01
     androidx
    -0.91
    Đặc
    -0.83
     leuke
    -0.82
     чаще
    -0.80
     Codable
    -0.80
     män
    -0.79
     Unión
    -0.79
     mezzo
    -0.77
     covid
    -0.77
    POSITIVE LOGITS
    println
    1.56
     println
    1.35
    NSNotification
    1.14
    KindOfClass
    1.05
    AtIndexPath
    1.02
     CGRectMake
    0.96
     AnyObject
    0.93
    tillo
    0.89
     Huffington
    0.87
    遺産
    0.87
    Activations Density 0.058%

    No Known Activations