© 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. 115873
    Prev
    Next
    INDEX
    Explanations

    contrasting conjunctions

    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
     khó
    -0.07
     although
    -0.07
    แต่
    -0.07
     esfuerzos
    -0.06
     પ્રય
    -0.06
     is
    -0.06
     but
    -0.06
     улучшения
    -0.06
    默默
    -0.06
     efforts
    -0.06
    POSITIVE LOGITS
     disg
    0.06
     hCG
    0.06
     preponder
    0.06
    ",
    0.06
     itd
    0.06
    什么的
    0.06
     upris
    0.06
       
    0.05
     COVID
    0.05
     unacceptable
    0.05
    Activations Density 0.042%

    No Known Activations