© 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. 128027
    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
     Reasoning
    -0.07
     ideology
    -0.06
     suspicions
    -0.06
     následuj
    -0.06
    uć
    -0.06
     aktuelle
    -0.06
     ifad
    -0.06
     current
    -0.06
     शानदार
    -0.06
     లేదా
    -0.06
    POSITIVE LOGITS
     भाज
    0.06
    String
    0.06
     gravity
    0.06
    hots
    0.06
    ";
    0.06
     law
    0.06
    雖
    0.06
     divulg
    0.06
     που
    0.05
     permettant
    0.05
    Activations Density 0.000%

    No Known Activations