© 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. 127964
    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
     непосредственно
    -0.06
    然後
    -0.06
    yk
    -0.05
    ㅅ
    -0.05
     вроде
    -0.05
    shell
    -0.05
    事項
    -0.05
     जितेंद्र
    -0.05
     Vander
    -0.05
    ស្ន
    -0.05
    POSITIVE LOGITS
     WIFI
    0.07
     amerikanischen
    0.07
    Nicolas
    0.06
     ভীত
    0.06
    Algun
    0.06
     himself
    0.06
    方に
    0.06
     Barbados
    0.06
     his
    0.06
     पड़ेगी
    0.06
    Activations Density 0.000%

    No Known Activations