© 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
    3. Gemma-3-12B
    5. 12-GEMMASCOPE-2-RES-16K
    7. 78
    Prev
    Next
    INDEX
    Explanations

    nationalities and associated topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_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
    िया
    0.70
     शिक्षकों
    0.67
     vô
    0.64
    اد
    0.64
    ين
    0.63
    ুর
    0.62
     każdy
    0.62
    ز
    0.62
    إذا
    0.61
    š
    0.60
    POSITIVE LOGITS
    land
    0.74
     manca
    0.72
    malign
    0.71
    ifting
    0.70
    illiant
    0.69
    cl
    0.69
    men
    0.69
    mag
    0.68
    to
    0.68
    mailed
    0.68
    Activations Density 1.116%

    No Known Activations