© 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. 31297
    Prev
    Next
    INDEX
    Explanations

    russia or russian

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

    Russia

    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
    शिलाजीत
    0.62
    دارة
    0.61
    뷸
    0.59
    errick
    0.54
    マータイヤ
    0.54
    फाली
    0.53
    轮胎
    0.52
    oribus
    0.52
    濑
    0.51
    Aeonium
    0.50
    POSITIVE LOGITS
     Russian
    2.23
     Moscow
    2.17
     Russia
    2.08
     러시아
    2.08
    Russian
    1.94
    ロシア
    1.93
     russian
    1.91
     Russians
    1.90
    Moscow
    1.90
    Russia
    1.86
    Activations Density 0.168%

    No Known Activations