© 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. 128070
    Prev
    Next
    INDEX
    Explanations

    code syntax and structure

    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
    Notification
    -0.07
     hvis
    -0.06
     Notification
    -0.06
     Protective
    -0.06
    Infos
    -0.05
    紓
    -0.05
     Opportunities
    -0.05
    श्त
    -0.05
    '])->
    -0.05
     Enquanto
    -0.05
    POSITIVE LOGITS
    বেলা
    0.06
     exhibition
    0.06
     the
    0.06
     апо
    0.06
     attractions
    0.06
     confidently
    0.06
    会议
    0.06
     வாய்
    0.06
     herramienta
    0.06
     unes
    0.06
    Activations Density 0.008%

    No Known Activations