© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 166729
    Prev
    Next
    INDEX
    Explanations

    international or nationality

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

    using set

    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
    Negative Logits
    DATA
    0.52
     generalizations
    0.49
     visualizations
    0.48
     визуа
    0.44
     어려
    0.44
     persuas
    0.43
     cảnh
    0.42
     تیار
    0.42
     archival
    0.41
    囵
    0.41
    POSITIVE LOGITS
     จริง
    0.54
    មាន
    0.50
     Austrian
    0.50
     Englishman
    0.49
     สัก
    0.48
     English
    0.48
     อังกฤษ
    0.48
     Su
    0.47
     Russians
    0.47
     เฉล
    0.46
    Activations Density 0.000%

    No Known Activations