© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116028
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
    Negative Logits
    任何
    -0.07
     будет
    -0.07
    在
    -0.06
     ځ
    -0.06
     ಯಾರ
    -0.06
     oldu
    -0.06
     எந்த
    -0.06
    你的
    -0.06
    ０
    -0.06
     ሙሉ
    -0.06
    POSITIVE LOGITS
     dozens
    0.07
     hundreds
    0.07
     unparalleled
    0.07
     thousands
    0.06
    後ろ
    0.06
     more
    0.06
     ক্ষত্র
    0.06
     الأن
    0.06
     seeing
    0.06
     elegance
    0.06
    Activations Density 0.042%

    No Known Activations