© 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. 127939
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ͝
    -0.06
     tecnologias
    -0.05
    रान
    -0.05
     tecnologías
    -0.05
    idea
    -0.05
     زن
    -0.05
    setSelected
    -0.05
     exiting
    -0.05
     technology
    -0.05
    topics
    -0.05
    POSITIVE LOGITS
    他的
    0.08
     一般
    0.07
    一般的
    0.07
     gedaan
    0.07
     нам
    0.07
     علاوه
    0.07
    一般
    0.06
     genellikle
    0.06
     njegov
    0.06
     Generally
    0.06
    Activations Density 0.000%

    No Known Activations