© 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. 128122
    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
     várias
    -0.07
     সঠিকভাবে
    -0.06
     vários
    -0.06
     ব্যয়
    -0.06
    写法
    -0.06
    ដែលអាច
    -0.06
     automatisch
    -0.06
     berapa
    -0.06
     automatically
    -0.06
     ট্র্যাক
    -0.06
    POSITIVE LOGITS
    、
    0.07
    trainer
    0.05
     annoy
    0.05
     મહે
    0.05
     দেখলে
    0.05
     gentle
    0.05
    তেই
    0.05
    ']['
    0.05
     none
    0.05
    日常
    0.05
    Activations Density 0.000%

    No Known Activations