© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7300
    Prev
    Next
    INDEX
    Explanations

    Swift programming language and related types

    np_acts-logits-general · gemini-2.5-flash-lite

    Swift code generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ichia
    0.47
    bufs
    0.43
     compds
    0.42
    ='';
    0.42
     চলে
    0.41
    orest
    0.41
     Kloster
    0.41
     Peruvian
    0.40
     $('#
    0.39
     ordination
    0.39
    POSITIVE LOGITS
    Swift
    1.41
     Swift
    1.35
    ("\(
    1.34
     "\(
    1.30
     UserDefaults
    1.29
     SwiftUI
    1.27
    UserDefaults
    1.26
    CGFloat
    1.24
    NSString
    1.20
     NSError
    1.20
    Activations Density 0.003%

    No Known Activations