© 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. 127989
    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
    ，
    -0.08
    制限
    -0.07
    单个
    -0.07
    ต่างๆ
    -0.06
    调整
    -0.06
     restric
    -0.06
    ,
    -0.06
    限制
    -0.06
     제한
    -0.06
    Despite
    -0.06
    POSITIVE LOGITS
     as
    0.09
    isional
    0.08
     ಏನು
    0.07
     valuable
    0.06
    북
    0.06
     این
    0.06
     rique
    0.06
     북
    0.06
     so
    0.06
     on
    0.06
    Activations Density 0.000%

    No Known Activations