© 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. 49508
    Prev
    Next
    INDEX
    Explanations

    native speaker introductions

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

    video components

    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
    .³
    0.44
     limiting
    0.44
     analytically
    0.43
     briefly
    0.43
     formative
    0.43
     included
    0.43
    äfte
    0.42
     homologous
    0.42
     enthalpies
    0.42
     coordinates
    0.42
    POSITIVE LOGITS
     VIDEO
    0.55
    🫡
    0.52
    VIDEO
    0.49
     ২০২২
    0.46
    video
    0.45
     GOVERNMENT
    0.45
    🫂
    0.43
     SwiftUI
    0.43
     فيديو
    0.42
    TikTok
    0.42
    Activations Density 0.000%

    No Known Activations