© 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. 128038
    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
     القيام
    -0.06
     engines
    -0.06
     جميع
    -0.06
    жет
    -0.06
     عملية
    -0.06
    جميع
    -0.06
     baile
    -0.06
     Konya
    -0.06
    সাম
    -0.06
    engines
    -0.06
    POSITIVE LOGITS
     interstate
    0.07
     permanent
    0.06
     Geographical
    0.06
     sparsely
    0.06
     ከአ
    0.06
    国道
    0.06
     attravers
    0.06
    permanent
    0.06
     государство
    0.06
    に通
    0.06
    Activations Density 0.000%

    No Known Activations