© 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. 128118
    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
     পুণ
    -0.07
     tightly
    -0.06
     you
    -0.06
     విధంగా
    -0.06
     να
    -0.06
    
    -0.06
     أن
    -0.06
    雖然
    -0.06
     инструмент
    -0.06
     although
    -0.06
    POSITIVE LOGITS
    -
    0.06
    ចែក
    0.06
     representante
    0.06
     reparación
    0.06
    只见
    0.06
     på
    0.05
    .
    0.05
    Най
    0.05
     소개
    0.05
    :
    0.05
    Activations Density 0.000%

    No Known Activations