© 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. 120957
    Prev
    Next
    INDEX
    Explanations

    json or xml success indicators

    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
     seen
    -0.07
     through
    -0.07
     with
    -0.06
     कॉलोनी
    -0.06
     bargains
    -0.06
     dengan
    -0.06
     চায়
    -0.06
     варианты
    -0.06
     by
    -0.06
     jin
    -0.06
    POSITIVE LOGITS
    Which
    0.08
     когато
    0.07
     처음
    0.07
     Which
    0.07
     kiedy
    0.06
     cuando
    0.06
     Earlier
    0.06
     WHICH
    0.06
     aumentada
    0.06
     także
    0.06
    Activations Density 0.013%

    No Known Activations