© 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. 115894
    Prev
    Next
    INDEX
    Explanations

    court of appeals

    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
     egyszerű
    -0.07
     свадь
    -0.06
    !
    -0.06
     such
    -0.06
     család
    -0.06
     फैमिली
    -0.06
     فاس
    -0.06
     простых
    -0.06
     gebruik
    -0.06
     ovulation
    -0.06
    POSITIVE LOGITS
     Occupational
    0.06
     if
    0.06
    Sorted
    0.06
     penalties
    0.06
    owały
    0.06
    忏
    0.05
    ഴിഞ്ഞ
    0.05
     diet
    0.05
     खर
    0.05
    Reflection
    0.05
    Activations Density 0.001%

    No Known Activations