© 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. 120982
    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
    individuals
    -0.07
    Còn
    -0.07
     còn
    -0.06
     individuals
    -0.06
     knowledge
    -0.06
     inoltre
    -0.06
    Recurs
    -0.06
     adicion
    -0.06
     supplementation
    -0.06
    uanya
    -0.06
    POSITIVE LOGITS
     полноцен
    0.06
     thrilling
    0.06
     sfida
    0.06
    ppable
    0.06
     photometric
    0.06
     AMAZING
    0.06
     continuous
    0.06
    相比
    0.06
     length
    0.05
     fifty
    0.05
    Activations Density 0.000%

    No Known Activations