© 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. 16218
    Prev
    Next
    INDEX
    Explanations

    programming keywords and symbols

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

    programming languages

    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
     RADIATION
    0.44
    稗
    0.39
     earrings
    0.38
     olefins
    0.38
     Mahoney
    0.38
     ।”
    0.38
     HYDRO
    0.37
     reso
    0.37
    耳
    0.37
    伯
    0.37
    POSITIVE LOGITS
     django
    0.66
    django
    0.64
     Symfony
    0.59
     PHP
    0.59
     SwiftUI
    0.55
    android
    0.54
     pygame
    0.54
     jQuery
    0.52
     Laravel
    0.52
    AspNetCore
    0.52
    Activations Density 0.129%

    No Known Activations