© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119116
    Prev
    Next
    INDEX
    Explanations

    test words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     समन्वय
    -0.08
     지금까지
    -0.07
    顾客
    -0.06
     nếu
    -0.06
     না
    -0.06
     delivery
    -0.06
     hasta
    -0.06
    ฤ
    -0.06
     até
    -0.06
     adjusting
    -0.06
    POSITIVE LOGITS
    测试
    0.07
    測試
    0.06
    itetty
    0.06
    テスト
    0.06
     परीक्षण
    0.06
     voltmeter
    0.06
    谁
    0.06
     اختبار
    0.06
    TEST
    0.05
     test
    0.05
    Activations Density 0.002%

    No Known Activations