© 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. 128107
    Prev
    Next
    INDEX
    Explanations

    "

    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
    Recent
    -0.06
     કુલ
    -0.06
    куда
    -0.06
    Similar
    -0.06
     demanded
    -0.06
    newer
    -0.06
    舧
    -0.06
     प्रभाव
    -0.06
     crew
    -0.06
    뷁
    -0.06
    POSITIVE LOGITS
     mengembangkan
    0.06
     groundwater
    0.06
    全世界
    0.06
     креди
    0.06
     is
    0.06
    どんどん
    0.06
     تاکید
    0.06
     σημα
    0.06
    给定
    0.06
     emphasizes
    0.06
    Activations Density 0.008%

    No Known Activations