© 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. 115991
    Prev
    Next
    INDEX
    Explanations

    python special method names

    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
     lors
    -0.06
     тощо
    -0.06
     That
    -0.06
    ण्याचा
    -0.06
     as
    -0.06
     हिमालय
    -0.06
    並且
    -0.06
     ل
    -0.06
     were
    -0.06
     One
    -0.06
    POSITIVE LOGITS
     amount
    0.06
    以外
    0.06
     abil
    0.06
     list
    0.06
    初始化
    0.06
    ូវ
    0.06
     Renner
    0.06
     altas
    0.05
     दायर
    0.05
    --,
    0.05
    Activations Density 0.001%

    No Known Activations