© 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. 116007
    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
     verantwoord
    -0.07
     Kyrgyzstan
    -0.06
     bevest
    -0.06
     Λ
    -0.06
    徃
    -0.06
     però
    -0.06
     खबर
    -0.06
    দারের
    -0.06
    FAILED
    -0.06
     دیا۔
    -0.06
    POSITIVE LOGITS
     two
    0.06
     key
    0.06
     karna
    0.05
    similarity
    0.05
    特性
    0.05
     are
    0.05
     %><%=
    0.05
    珏
    0.05
    സീ
    0.05
     jeśli
    0.05
    Activations Density 0.000%

    No Known Activations