© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3760
    Prev
    Next
    INDEX
    Explanations

    importantly

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

    import statements for programming modules

    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
    एस
    0.41
    ಎ
    0.39
    ิจ
    0.37
     Beaucoup
    0.37
    ெல்லி
    0.36
    瓊
    0.36
     consape
    0.36
    덴
    0.35
    रा
    0.35
    iense
    0.35
    POSITIVE LOGITS
     './
    0.66
     "./
    0.61
    ances
    0.59
     numpy
    0.59
    anced
    0.59
     UIKit
    0.59
     tkinter
    0.55
    anc
    0.55
     React
    0.55
     SwiftUI
    0.54
    Activations Density 0.007%

    No Known Activations