© 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. 120864
    Prev
    Next
    INDEX
    Explanations

    class,Company,resource,dataset

    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
    combine
    -0.06
     łącz
    -0.06
     combined
    -0.06
     vollständig
    -0.06
    combined
    -0.06
     congested
    -0.06
     тща
    -0.06
     INFIN
    -0.05
     but
    -0.05
     ممکن
    -0.05
    POSITIVE LOGITS
    HALL
    0.06
     encryption
    0.06
    撸
    0.06
    éről
    0.06
    バター
    0.06
     take
    0.06
     also
    0.06
     commitment
    0.06
    하기
    0.05
     Commitment
    0.05
    Activations Density 0.006%

    No Known Activations