© 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. 120895
    Prev
    Next
    INDEX
    Explanations

    legal parties (appellant, appellee, petitioner)

    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
    ដែល
    -0.07
     that
    -0.07
     दट
    -0.07
     RECOMMEND
    -0.06
     kterou
    -0.06
     തര
    -0.06
     enthous
    -0.06
    麻煩
    -0.06
     olyan
    -0.06
     kaki
    -0.06
    POSITIVE LOGITS
     or
    0.07
     কয়েকটি
    0.06
    或
    0.06
     nasze
    0.06
     지난해
    0.06
     أو
    0.06
    Local
    0.06
    Non
    0.06
    ),”
    0.05
    获得
    0.05
    Activations Density 0.001%

    No Known Activations