© 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. 355
    Prev
    Next
    INDEX
    Explanations

    foreign language origins

    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
    но
    0.89
    ن
    0.83
    ر
    0.78
    א
    0.77
    ان
    0.76
    ла
    0.73
    د
    0.73
    त
    0.71
    ش
    0.71
    न
    0.68
    POSITIVE LOGITS
     assassin
    0.48
     fois
    0.47
     storied
    0.47
     unscrupulous
    0.47
     Prescription
    0.45
    ς
    0.45
     imprisoned
    0.44
     underrated
    0.44
    ্লাহ
    0.43
     lanç
    0.43
    Activations Density 0.595%

    No Known Activations