© 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. 128140
    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
     is
    -0.08
     все
    -0.07
     குழந்தையின்
    -0.06
     крайне
    -0.06
     ഇവിടെ
    -0.06
     без
    -0.06
     jambes
    -0.06
     consecuencias
    -0.06
     специа
    -0.06
     comes
    -0.06
    POSITIVE LOGITS
    被告
    0.05
    seeking
    0.05
     inoltre
    0.05
     зае
    0.05
    Also
    0.05
    Finder
    0.05
     între
    0.05
    ALSO
    0.05
     sought
    0.05
    ample
    0.05
    Activations Density 0.000%

    No Known Activations