© 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. 120922
    Prev
    Next
    INDEX
    Explanations

    version numbers

    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
     Nour
    -0.06
     jaoks
    -0.06
    umpang
    -0.06
     শাহ
    -0.06
    letas
    -0.06
     leur
    -0.06
    ತರ
    -0.06
    shares
    -0.06
    করে
    -0.06
     듯
    -0.06
    POSITIVE LOGITS
     آینده
    0.06
    变
    0.06
    變
    0.06
     ভ্রমণ
    0.06
     শনিবার
    0.06
    changing
    0.06
     দুর্নীতি
    0.06
     oxi
    0.06
     DECEMBER
    0.06
     Released
    0.06
    Activations Density 0.005%

    No Known Activations