© 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. 120874
    Prev
    Next
    INDEX
    Explanations

    first mention of sequel, year, or new album

    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
    之际
    -0.07
     upcoming
    -0.07
     impending
    -0.07
     শিগ
    -0.07
     shortly
    -0.06
    不久
    -0.06
     subgroups
    -0.06
    即将
    -0.06
     year
    -0.06
     după
    -0.06
    POSITIVE LOGITS
     construcción
    0.07
     primero
    0.06
     construir
    0.06
    ｕ
    0.06
     вони
    0.06
     मठ
    0.06
     otvor
    0.06
    都能
    0.06
     eerste
    0.06
     ahora
    0.06
    Activations Density 0.015%

    No Known Activations