© 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. 127924
    Prev
    Next
    INDEX
    Explanations

    club names and football seasons

    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
    appName
    -0.06
     новую
    -0.06
     চারটি
    -0.06
    ))){
    -0.06
     occupants
    -0.06
     новой
    -0.06
     narrative
    -0.06
     marry
    -0.06
     northern
    -0.06
     বী
    -0.06
    POSITIVE LOGITS
     অজ্ঞাত
    0.06
     inaccuracy
    0.06
    archa
    0.06
     międzynarod
    0.06
     wichtiger
    0.06
     unknown
    0.06
    unknown
    0.06
     efforts
    0.06
     Efforts
    0.06
     demolition
    0.06
    Activations Density 0.011%

    No Known Activations