© 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-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17707
    Prev
    Next
    INDEX
    Explanations

    Russia and Moscow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    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
    텐
    0.40
    assertEqual
    0.39
     situe
    0.39
     पटना
    0.39
     बिहार
    0.38
    toBytes
    0.38
    ﮟ
    0.38
     百
    0.38
    陂
    0.38
    ㄗ
    0.38
    POSITIVE LOGITS
     Russian
    1.32
     Moscow
    1.27
     Russia
    1.25
    Moscow
    1.23
     러시아
    1.23
    Russian
    1.23
    俄罗斯
    1.20
    ロシア
    1.18
     ரஷ்ய
    1.17
     रूसी
    1.16
    Activations Density 0.038%

    No Known Activations