© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1981
    Prev
    Next
    INDEX
    Explanations

    foreign language sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
     ١
    1.80
     최초
    1.75
     Ло
    1.74
     Кон
    1.73
     Не
    1.72
     执行
    1.69
     माननीय
    1.68
     DECIMAL
    1.67
     Пи
    1.66
     १
    1.65
    POSITIVE LOGITS
    こちらも
    1.18
     äuß
    0.90
    driven
    0.86
    nya
    0.85
     inset
    0.85
    hört
    0.76
    Õ
    0.76
    后者
    0.75
     keduanya
    0.74
    …。
    0.74
    Activations Density 0.231%

    No Known Activations