© 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. 121077
    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
     it
    -0.09
     if
    -0.07
     by
    -0.07
    它
    -0.07
     but
    -0.06
     and
    -0.06
    它可以
    -0.06
    §
    -0.06
     ಅದನ್ನು
    -0.06
    ซื้อ
    -0.06
    POSITIVE LOGITS
     fehlen
    0.06
     pharmaceuticals
    0.06
     aforementioned
    0.06
    Significant
    0.06
     モン
    0.06
     FYI
    0.06
     horticulture
    0.05
     सापेक्ष
    0.05
    ９
    0.05
     गौरतलब
    0.05
    Activations Density 0.000%

    No Known Activations