© 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. 128227
    Prev
    Next
    INDEX
    Explanations

    HTML tags and attributes

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Lanc
    -0.07
     OpenGL
    -0.07
     Whenever
    -0.06
    の状態
    -0.06
    Whenever
    -0.06
     LANC
    -0.06
     recorded
    -0.06
     species
    -0.06
     Sempre
    -0.06
     además
    -0.06
    POSITIVE LOGITS
     by
    0.06
     in
    0.06
     dzieci
    0.06
     hasta
    0.06
     przez
    0.06
     feste
    0.06
     dvije
    0.06
     heps
    0.06
    俬
    0.06
     cuz
    0.06
    Activations Density 0.007%

    No Known Activations