© 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. 127966
    Prev
    Next
    INDEX
    Explanations

    magnesium

    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
     mayoral
    -0.07
     তোমার
    -0.06
    DNA
    -0.06
     internship
    -0.06
    \\\\
    -0.06
     City
    -0.06
    🐀
    -0.06
    “”
    -0.06
    itte
    -0.06
     Language
    -0.06
    POSITIVE LOGITS
     rectángulo
    0.06
    ৫
    0.06
     dislike
    0.06
     паў
    0.06
     calmness
    0.06
     Tahiti
    0.06
     അദ്ദേഹ
    0.06
    🤲
    0.06
    他是
    0.06
    thymeleaf
    0.06
    Activations Density 0.012%

    No Known Activations