© 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. 127918
    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
    其
    -0.07
     aparentemente
    -0.06
     क्रमशः
    -0.06
     их
    -0.06
     其
    -0.06
     jejich
    -0.06
    Their
    -0.06
    全局
    -0.06
     leurs
    -0.05
     अकेले
    -0.05
    POSITIVE LOGITS
    MASK
    0.06
    ździe
    0.06
    acknowledge
    0.06
     Masks
    0.06
     masks
    0.06
    開設
    0.06
     FEE
    0.06
     frail
    0.05
     perishable
    0.05
     siswa
    0.05
    Activations Density 0.000%

    No Known Activations