© 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. 116166
    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
     ecc
    -0.06
    ても
    -0.06
    這裡是
    -0.06
    ится
    -0.06
    arken
    -0.06
    zą
    -0.06
     each
    -0.06
     <--
    -0.06
     วัด
    -0.06
     abbreviated
    -0.06
    POSITIVE LOGITS
     тормо
    0.06
     flocks
    0.06
     misinterpreted
    0.06
     matching
    0.06
     پیدا
    0.06
     unknow
    0.06
     overlooking
    0.06
     paradox
    0.06
    あなたが
    0.06
     দু
    0.06
    Activations Density 0.000%

    No Known Activations