© 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. 116108
    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
     COMPARE
    -0.06
    🔹
    -0.06
     compare
    -0.06
    Comparison
    -0.06
    Comparing
    -0.06
    全長
    -0.06
     comparison
    -0.06
     Vergleich
    -0.06
                
    -0.06
     длин
    -0.06
    POSITIVE LOGITS
     challeng
    0.06
     musí
    0.06
     महाराष्ट
    0.06
     muss
    0.06
     prerequisite
    0.06
     Chow
    0.06
     خلا
    0.06
     trinity
    0.06
     domesticated
    0.06
     Surreal
    0.06
    Activations Density 0.000%

    No Known Activations