© 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. 116036
    Prev
    Next
    INDEX
    Explanations

    intended to diagnose

    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
     would
    -0.07
     but
    -0.06
     kilka
    -0.06
     choirs
    -0.06
     ถึง
    -0.06
    ចាប់
    -0.06
    口袋
    -0.06
     κό
    -0.06
     αλλά
    -0.06
     choir
    -0.06
    POSITIVE LOGITS
     또한
    0.07
     inoltre
    0.06
     также
    0.06
    തേ
    0.06
     состояния
    0.06
    unque
    0.06
    ваясь
    0.06
     reciproc
    0.06
    前半
    0.06
    ที่เรา
    0.06
    Activations Density 0.001%

    No Known Activations