© 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. 121053
    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
     रोग
    -0.06
     poor
    -0.06
    複数
    -0.06
     teda
    -0.06
     south
    -0.05
     outside
    -0.05
     also
    -0.05
    と思いますが
    -0.05
    ቱም
    -0.05
     tedy
    -0.05
    POSITIVE LOGITS
     entsprechenden
    0.07
     maximise
    0.06
    ANY
    0.06
    Chill
    0.06
     ঘনিষ্ঠ
    0.06
    writeByte
    0.06
    iany
    0.06
     vuonna
    0.06
    ிகளில்
    0.06
    .&
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.