© 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. 128245
    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
    Not in Any Lists

    No Comments

    Negative Logits
     perplexed
    -0.07
     এই
    -0.07
    常に
    -0.06
     monastery
    -0.06
     معاد
    -0.06
    Sto
    -0.06
     že
    -0.06
     पुरे
    -0.06
     constamment
    -0.06
    鱒
    -0.06
    POSITIVE LOGITS
     my
    0.08
     지난해
    0.07
     current
    0.07
    霾
    0.06
     моя
    0.06
     kids
    0.06
    今年
    0.05
     janvier
    0.05
     Manch
    0.05
    зываем
    0.05
    Activations Density 0.000%

    No Known Activations