© 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. 115933
    Prev
    Next
    INDEX
    Explanations

    bottom corner or edge

    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
     tief
    -0.06
    Check
    -0.06
    ढी
    -0.06
    通常
    -0.06
     Kole
    -0.06
     ফেডার
    -0.06
     courant
    -0.06
    ൾ
    -0.06
     गर्ल
    -0.05
     Markus
    -0.05
    POSITIVE LOGITS
    出来了
    0.06
     enlargement
    0.06
     yeni
    0.06
    Scenes
    0.06
     دو
    0.06
     nueva
    0.06
     صع
    0.06
     respondió
    0.06
     увеличения
    0.06
    容器
    0.06
    Activations Density 0.002%

    No Known Activations