© 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. 16-GEMMASCOPE-2-RES-262K
    7. 48176
    Prev
    Next
    INDEX
    Explanations

    Tibet and Tibetan Plateau

    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_16_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
    る
    0.71
     vigour
    0.70
    تان
    0.67
    ق
    0.66
    ر
    0.66
     endeavours
    0.65
    τ
    0.64
    ли
    0.63
    レー
    0.61
    仮
    0.61
    POSITIVE LOGITS
     Lhasa
    0.78
    liği
    0.75
     Tibet
    0.69
     sacr
    0.69
     Menlo
    0.69
     Pantheon
    0.67
     Tibetan
    0.66
     Mainland
    0.64
    amera
    0.63
    os
    0.62
    Activations Density 0.003%

    No Known Activations