© 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. 115917
    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
     ವರ್ಷ
    -0.07
     sering
    -0.06
    下列
    -0.06
    如同
    -0.06
    АР
    -0.06
     cualquiera
    -0.06
    全年
    -0.06
    下面的
    -0.06
     can
    -0.06
    如下
    -0.06
    POSITIVE LOGITS
     pajamas
    0.06
    টিয়ে
    0.06
     correctly
    0.06
     contribu
    0.06
    tv
    0.06
     having
    0.06
     digested
    0.06
     საკ
    0.06
     लड़का
    0.05
     Worthing
    0.05
    Activations Density 0.000%

    No Known Activations