© 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. 127928
    Prev
    Next
    INDEX
    Explanations

    scientific, technical, or mathematical terms

    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
     orang
    -0.06
    жно
    -0.06
     Walther
    -0.06
    인
    -0.06
     স্বাদ
    -0.06
     yell
    -0.06
    deserved
    -0.06
    mob
    -0.06
     posséd
    -0.05
    krank
    -0.05
    POSITIVE LOGITS
     nhằm
    0.06
     അല്ലെങ്കിൽ
    0.06
     biblioteca
    0.06
     titulada
    0.06
     PCB
    0.06
    เพื่อ
    0.06
    为了
    0.06
     부분이
    0.06
     부분을
    0.06
     olmadan
    0.06
    Activations Density 0.001%

    No Known Activations