© 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. 115896
    Prev
    Next
    INDEX
    Explanations

    key in plist or xml

    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
     its
    -0.09
     actual
    -0.07
     زبان
    -0.06
     non
    -0.06
     за
    -0.06
     факти
    -0.06
    であれば
    -0.06
     почти
    -0.06
     Actual
    -0.06
     તેની
    -0.06
    POSITIVE LOGITS
     هذه
    0.07
     questa
    0.07
     diese
    0.06
     cette
    0.06
     weder
    0.06
    この
    0.06
     denna
    0.06
     ás
    0.06
     deze
    0.06
     connects
    0.06
    Activations Density 0.002%

    No Known Activations