© 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
    2. Gemma-3-27B
    3. 40-GEMMASCOPE-2-RES-16K
    4. 11576
    Prev
    Next
    INDEX
    Explanations

    Taiwanese hardware

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

    Taiwan

    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_40_width_16k_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
    仅仅
    0.51
    趔
    0.51
    随后
    0.51
    Ҳ
    0.51
    Manchester
    0.50
    Қ
    0.50
    撾
    0.49
    қи
    0.48
    十壹章
    0.48
    жён
    0.47
    POSITIVE LOGITS
     Taiwan
    2.17
     Taiwanese
    2.11
    Taiwan
    2.06
     Taipei
    1.95
     taiwan
    1.93
    台湾
    1.84
    台北
    1.79
    台灣
    1.68
     Đài
    1.61
    臺灣
    1.52
    Activations Density 0.236%

    No Known Activations