© 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. 109766
    Prev
    Next
    INDEX
    Explanations

    Singapore, government, national service

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

    Singapore General Hospital

    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
     kerana
    0.49
    杪
    0.47
    ovaný
    0.45
    withtag
    0.44
    hamdulillah
    0.44
    awati
    0.44
     disponibilités
    0.44
    結構
    0.43
     iaitu
    0.43
    ាត
    0.43
    POSITIVE LOGITS
    Singapore
    0.77
     Singapore
    0.75
    新加坡
    0.68
     सिंगापुर
    0.66
     singapore
    0.59
    SING
    0.57
     싱
    0.56
     Singapura
    0.54
    加坡
    0.52
     SING
    0.52
    Activations Density 0.097%

    No Known Activations