© 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. 127963
    Prev
    Next
    INDEX
    Explanations

    authors and columnists

    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
     obiekt
    -0.06
    politik
    -0.06
     politik
    -0.06
     económico
    -0.06
     exporting
    -0.06
     exported
    -0.06
     básico
    -0.06
     commands
    -0.06
     directories
    -0.06
    旨
    -0.06
    POSITIVE LOGITS
    乸
    0.07
     תק
    0.06
     sábado
    0.06
     begleitet
    0.06
     रविवार
    0.06
     চিকিৎ
    0.06
     společ
    0.06
    于是
    0.06
     Questo
    0.06
     jueves
    0.06
    Activations Density 0.013%

    No Known Activations