© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 15053
    Prev
    Next
    INDEX
    Explanations

    Taylor Swift

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

    Taylor Swift and Swift language

    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_31_width_262k_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
    ikesh
    0.43
    auc
    0.42
    মাহ
    0.40
    ﾈ
    0.40
    entar
    0.39
    Translate
    0.39
    巖
    0.39
    focus
    0.39
    *[
    0.39
     "@{
    0.38
    POSITIVE LOGITS
     Swift
    0.82
    Swift
    0.72
     SwiftUI
    0.63
    swift
    0.59
     swift
    0.56
     Xcode
    0.50
     objc
    0.50
    ্বেও
    0.48
     awarding
    0.47
     RxSwift
    0.45
    Activations Density 0.007%

    No Known Activations