© 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. 128141
    Prev
    Next
    INDEX
    Explanations

    digits followed by punctuation

    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
     would
    -0.06
    डेन
    -0.06
    hade
    -0.06
     نگاه
    -0.06
     arasındaki
    -0.06
    مام
    -0.06
    iges
    -0.06
    遇到的
    -0.06
     fierce
    -0.06
    ध्ये
    -0.06
    POSITIVE LOGITS
     innych
    0.06
     おり
    0.06
     通过
    0.06
     Butt
    0.06
     مشتمل
    0.06
     zowel
    0.06
     اثنين
    0.06
    representing
    0.06
     하루
    0.06
     सकती
    0.06
    Activations Density 0.001%

    No Known Activations