© 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. 115865
    Prev
    Next
    INDEX
    Explanations

    Online, Wednesday, Q

    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
    either
    -0.06
    漂亮的
    -0.06
     자랑
    -0.06
     न्यूनतम
    -0.06
    remainder
    -0.06
     ಒಂದು
    -0.06
    当中
    -0.05
     પણ
    -0.05
    slack
    -0.05
    នៃ
    -0.05
    POSITIVE LOGITS
     related
    0.08
     관련
    0.06
    Related
    0.06
    相關
    0.06
     svoj
    0.06
     relates
    0.06
     כדי
    0.06
    影響
    0.06
     svoje
    0.06
     অনুরূপ
    0.06
    Activations Density 0.002%

    No Known Activations