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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 27229
    Prev
    Next
    INDEX
    Explanations

    Ukrainian and Belarusian geography

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     alot
    0.61
    썻
    0.54
     velké
    0.49
    cusson
    0.49
    ක්‍
    0.49
     atleast
    0.48
     seperate
    0.48
    部份
    0.47
     upwards
    0.46
     monies
    0.46
    POSITIVE LOGITS
     peculiarities
    0.82
     Kyiv
    0.81
     Ukrainian
    0.75
     Belarusian
    0.74
     Kharkiv
    0.74
     С
    0.70
     Ukraine
    0.68
     Crimean
    0.67
     Belarus
    0.66
     Crimea
    0.66
    Activations Density 0.011%

    No Known Activations