© 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. 116144
    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
    Not in Any Lists

    No Comments

    Negative Logits
    ாளர்கள்
    -0.07
     speculated
    -0.06
     spared
    -0.06
     кожен
    -0.06
     have
    -0.06
    Have
    -0.06
     types
    -0.06
     need
    -0.06
     theyre
    -0.06
     decoding
    -0.06
    POSITIVE LOGITS
     the
    0.09
     also
    0.08
     także
    0.08
     também
    0.07
     también
    0.07
    后者
    0.07
     также
    0.06
     tudi
    0.06
     luôn
    0.06
     latter
    0.06
    Activations Density 0.000%

    No Known Activations