© 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. 120978
    Prev
    Next
    INDEX
    Explanations

    LLC, Inc., Foundation, Yahoo, Apple

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     on
    -0.08
     내가
    -0.07
     моей
    -0.06
     my
    -0.06
     protecting
    -0.06
     uden
    -0.06
     I
    -0.06
     दरवाजे
    -0.06
    זר
    -0.06
     ekstra
    -0.06
    POSITIVE LOGITS
     disregard
    0.08
    所以
    0.07
     somewhat
    0.07
     dissimilar
    0.07
     departs
    0.06
    راتيج
    0.06
     chỉ
    0.06
     hanya
    0.06
     completely
    0.06
     disreg
    0.06
    Activations Density 0.005%

    No Known Activations