© 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. 129961
    Prev
    Next
    INDEX
    Explanations

    names of people

    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
     μπορεί
    -0.08
     прия
    -0.08
     ड्रिल
    -0.07
     modifié
    -0.07
     può
    -0.06
     mobilier
    -0.06
     কর্তৃক
    -0.06
     verschil
    -0.06
     ដើម្បី
    -0.06
     différences
    -0.06
    POSITIVE LOGITS
    .
    0.06
     likewise
    0.06
    гда
    0.06
    dout
    0.06
     operational
    0.06
    -
    0.06
    online
    0.06
     -
    0.05
     high
    0.05
     cardiovascular
    0.05
    Activations Density 0.005%

    No Known Activations