© 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. 120991
    Prev
    Next
    INDEX
    Explanations

    car models or years

    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
     foodie
    -0.07
    These
    -0.06
     diffusione
    -0.06
    udging
    -0.06
     chup
    -0.06
    大多数
    -0.06
     hinch
    -0.06
     toplum
    -0.06
     Arabidopsis
    -0.06
     ആദ്യ
    -0.06
    POSITIVE LOGITS
     올해
    0.07
    百年
    0.06
     불편
    0.06
    parse
    0.06
     아름
    0.06
    今年も
    0.06
    今年は
    0.06
    幸福
    0.06
    start
    0.05
    今年の
    0.05
    Activations Density 0.026%

    No Known Activations