© 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. 116107
    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
     surrounded
    -0.06
     göst
    -0.06
    浯
    -0.06
    周围
    -0.06
     examen
    -0.06
    గ్
    -0.06
     hareket
    -0.06
     다음과
    -0.05
     אחת
    -0.05
     at
    -0.05
    POSITIVE LOGITS
     innovative
    0.06
     விவசாய
    0.06
     blended
    0.06
    வருக
    0.06
     ‍
    0.06
     khái
    0.06
    就知道
    0.06
     இதுவரை
    0.06
     लेटेस्ट
    0.05
    मिनी
    0.05
    Activations Density 0.000%

    No Known Activations