© 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. 116105
    Prev
    Next
    INDEX
    Explanations

    court names and locations

    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
    Not in Any Lists

    No Comments

    Negative Logits
     ஒரு
    -0.07
     우리는
    -0.06
     ჩვენ
    -0.06
     groundbreaking
    -0.06
     đảo
    -0.06
     పాటు
    -0.06
    Bollywood
    -0.06
    支部
    -0.06
     tulaj
    -0.06
     మనం
    -0.06
    POSITIVE LOGITS
     із
    0.06
     BUT
    0.06
    3
    0.06
    立
    0.06
    BUT
    0.06
    ☺
    0.06
     ਤਾਂ
    0.05
    ববার
    0.05
    ,’’
    0.05
     EXCEPT
    0.05
    Activations Density 0.005%

    No Known Activations