© 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. 121045
    Prev
    Next
    INDEX
    Explanations

    strategies, states, or past actions

    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
    最后
    -0.06
     optar
    -0.06
     chọn
    -0.06
    を選ぶ
    -0.06
    OPT
    -0.06
     deine
    -0.06
     opting
    -0.06
    ilihan
    -0.06
     اختيار
    -0.06
    opt
    -0.06
    POSITIVE LOGITS
     njegov
    0.07
     его
    0.07
     njegove
    0.06
     बाजारों
    0.06
     it
    0.06
    
    0.06
     deoarece
    0.06
     उनमें
    0.06
     față
    0.06
     cependant
    0.06
    Activations Density 0.025%

    No Known Activations