© 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. 120920
    Prev
    Next
    INDEX
    Explanations

    ( rounds )

    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
     including
    -0.08
     at
    -0.08
     may
    -0.08
     can
    -0.07
     no
    -0.07
     we
    -0.07
     in
    -0.07
     by
    -0.07
     on
    -0.07
     etc
    -0.07
    POSITIVE LOGITS
    更
    0.07
    使用
    0.07
    一个
    0.07
    一個
    0.07
    ）
    0.07
     магазине
    0.06
    長い
    0.06
    同时
    0.06
    是一个
    0.06
     stiffer
    0.06
    Activations Density 0.001%

    No Known Activations