© 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. 127973
    Prev
    Next
    INDEX
    Explanations

    sales and technical terms

    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
    จริงๆ
    -0.07
    封装
    -0.06
    𝟏
    -0.06
     ১৫
    -0.06
    npmjs
    -0.06
    麽
    -0.06
     перед
    -0.06
     jeszcze
    -0.06
     знаем
    -0.06
    跹
    -0.06
    POSITIVE LOGITS
     makes
    0.08
     делает
    0.06
     र
    0.06
     bland
    0.06
    makes
    0.06
    作战
    0.05
     등의
    0.05
     সমালো
    0.05
     thence
    0.05
     тощо
    0.05
    Activations Density 0.359%

    No Known Activations