© 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. 120844
    Prev
    Next
    INDEX
    Explanations

    image recording and display

    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
     innovations
    -0.06
     addTo
    -0.06
     Armor
    -0.06
     paintbrush
    -0.06
     innovation
    -0.06
     डिज
    -0.06
     unrelenting
    -0.06
    addTo
    -0.06
    设计的
    -0.06
     पीठ
    -0.06
    POSITIVE LOGITS
     после
    0.07
    源码
    0.06
     після
    0.06
     get
    0.06
     (
    0.06
    чный
    0.06
    级别
    0.06
     الحصول
    0.06
     after
    0.06
     uzyska
    0.06
    Activations Density 0.003%

    No Known Activations