© 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. 121046
    Prev
    Next
    INDEX
    Explanations

    year-on-year

    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
     നമ്മുടെ
    -0.06
     наши
    -0.06
    আমাদের
    -0.06
     આપણા
    -0.06
     nossa
    -0.06
    我们的
    -0.06
     committed
    -0.06
    约定
    -0.06
     চিন্তা
    -0.06
     nossas
    -0.06
    POSITIVE LOGITS
    上記
    0.07
     mno
    0.06
     टाइम्स
    0.06
     गौरतलब
    0.06
     erhielt
    0.06
    公式サイト
    0.06
    გუ
    0.06
     milliliters
    0.06
    +')
    0.06
     sĩ
    0.06
    Activations Density 0.005%

    No Known Activations