© 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. 120909
    Prev
    Next
    INDEX
    Explanations

    methodological quality and evaluation

    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
     ডান
    -0.06
    !
    -0.06
    截
    -0.06
     évalu
    -0.05
     বিচারের
    -0.05
     बंट
    -0.05
    往往
    -0.05
    print
    -0.05
     harus
    -0.05
    Shannon
    -0.05
    POSITIVE LOGITS
     perpetual
    0.06
     здоровья
    0.06
    可能性
    0.06
    MongoClient
    0.06
    家庭
    0.06
     geopolitical
    0.06
     disponíveis
    0.06
     warmth
    0.06
    ек
    0.06
     एकज
    0.06
    Activations Density 0.003%

    No Known Activations