© 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. 121004
    Prev
    Next
    INDEX
    Explanations

    special characters and accented letters

    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
     there
    -0.07
     इस
    -0.07
     この
    -0.07
    Currently
    -0.07
     between
    -0.07
     under
    -0.06
     actuellement
    -0.06
    There
    -0.06
     между
    -0.06
     சிற
    -0.06
    POSITIVE LOGITS
     тих
    0.07
     BASE
    0.06
     SW
    0.06
    鮨
    0.06
     eigene
    0.06
     digitally
    0.06
    Madrid
    0.06
    本地
    0.06
     eksempel
    0.06
    yre
    0.06
    Activations Density 0.005%

    No Known Activations