© 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. 13128
    Prev
    Next
    INDEX
    Explanations

    Russian higher education and Yakutia

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

    Russian language and science

    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
    éntesis
    0.73
    ającym
    0.71
    tać
    0.67
    rawdę
    0.66
    숴
    0.64
    ziała
    0.63
    awsze
    0.62
    ζο
    0.62
    ógł
    0.61
     więks
    0.60
    POSITIVE LOGITS
     С
    0.95
     Russian
    0.95
    С
    0.91
     Н
    0.89
     Moscow
    0.87
     Т
    0.86
     У
    0.86
     Belarusian
    0.86
     М
    0.85
     В
    0.82
    Activations Density 0.056%

    No Known Activations