© 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. 116019
    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
     agreeable
    -0.06
     Esso
    -0.06
    Doing
    -0.06
     пытается
    -0.06
     по
    -0.06
     beide
    -0.06
     dando
    -0.06
    లోని
    -0.06
    ほぼ
    -0.06
     Erschein
    -0.06
    POSITIVE LOGITS
     ア
    0.06
     deze
    0.06
    MEDIA
    0.06
    תו
    0.06
     বৈশিষ্ট
    0.06
     outcomes
    0.06
    னித
    0.06
     سمجھ
    0.06
    ंदा
    0.06
     caminos
    0.06
    Activations Density 0.000%

    No Known Activations