© 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. 115905
    Prev
    Next
    INDEX
    Explanations

    fluoroscopic computerized dynamic laser fragment length

    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
     நில
    -0.06
    Can
    -0.06
    Black
    -0.06
    По
    -0.06
     small
    -0.06
     при
    -0.06
    White
    -0.06
     Puede
    -0.06
     может
    -0.06
     не
    -0.06
    POSITIVE LOGITS
     这个
    0.08
     এখন
    0.07
     which
    0.07
    ﷺ
    0.07
     我們
    0.07
     この
    0.07
     elucid
    0.07
    ̶
    0.06
     این
    0.06
     这
    0.06
    Activations Density 0.017%

    No Known Activations