© 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. 121052
    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
     unaltered
    -0.06
    Firstly
    -0.06
     innocuous
    -0.06
     প্রথমেই
    -0.06
     incredibly
    -0.06
     হোটেলে
    -0.06
     firstly
    -0.06
    ergy
    -0.06
    esor
    -0.05
     horribly
    -0.05
    POSITIVE LOGITS
     mỗi
    0.07
     masing
    0.07
    缺少
    0.07
    各
    0.07
     Declar
    0.06
     buenas
    0.06
    Dark
    0.06
     jeder
    0.06
    each
    0.06
     каждая
    0.06
    Activations Density 0.000%

    No Known Activations