© 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. 115872
    Prev
    Next
    INDEX
    Explanations

    package name placeholders

    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
    両
    -0.06
     ф
    -0.06
    通过
    -0.06
     período
    -0.06
    䩕
    -0.06
    飞行
    -0.06
     পরিমাণে
    -0.05
     डॉलर
    -0.05
    饅
    -0.05
    如下图
    -0.05
    POSITIVE LOGITS
     કોઈ
    0.07
     किसी
    0.07
     weist
    0.07
     SOME
    0.06
     ইনি
    0.06
     assures
    0.06
     specifics
    0.06
     vurg
    0.06
     hetzelfde
    0.06
     requisitos
    0.06
    Activations Density 0.002%

    No Known Activations