© 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. 116052
    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
     gyd
    -0.07
     presque
    -0.06
     বিপক্ষে
    -0.06
     styl
    -0.06
    maximum
    -0.06
    幾乎
    -0.06
     trx
    -0.06
     ಯು
    -0.06
     opposes
    -0.06
    Maximum
    -0.06
    POSITIVE LOGITS
     informacija
    0.06
     দুইটি
    0.06
    ="#"
    0.06
     CCTV
    0.06
     دریا
    0.06
     információ
    0.06
     인식
    0.06
     mediocre
    0.06
    obtain
    0.06
    Cup
    0.06
    Activations Density 0.000%

    No Known Activations