© 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. 120983
    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
     other
    -0.07
     otros
    -0.07
     иных
    -0.06
     свобод
    -0.06
     другие
    -0.06
    から
    -0.06
     equating
    -0.06
     другим
    -0.06
     ЖК
    -0.06
     Multif
    -0.06
    POSITIVE LOGITS
     incredibly
    0.07
    itudinal
    0.06
    working
    0.06
     potrebbero
    0.06
     quando
    0.06
    قد
    0.06
    eeee
    0.06
     could
    0.06
     (/
    0.06
    폄
    0.05
    Activations Density 0.000%

    No Known Activations