© 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. 127910
    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
    훗
    -0.07
     только
    -0.06
     decadent
    -0.06
    ᓵ
    -0.06
     eclipsed
    -0.06
     chefe
    -0.06
    上也
    -0.06
     ლ
    -0.06
     only
    -0.06
     درخواست
    -0.06
    POSITIVE LOGITS
     raster
    0.06
    uv
    0.06
     UNHCR
    0.06
     Humanitarian
    0.06
     presumably
    0.06
    tope
    0.06
     deont
    0.05
     constructed
    0.05
    vironment
    0.05
     ইলেক্ট্রোলাই
    0.05
    Activations Density 0.010%

    No Known Activations