© 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. 116151
    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
     eternally
    -0.07
     soprattutto
    -0.06
     sobretudo
    -0.06
     ಶಿವ
    -0.06
    carn
    -0.06
     bount
    -0.06
     brutally
    -0.06
     numerose
    -0.06
     lovely
    -0.06
     drastically
    -0.06
    POSITIVE LOGITS
     типа
    0.06
    odium
    0.06
    (?
    0.06
    ,
    0.05
    を開始
    0.05
    স্থলে
    0.05
    bred
    0.05
     به
    0.05
    स्तिक
    0.05
     sera
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.