© 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. 128021
    Prev
    Next
    INDEX
    Explanations

    HTML tags

    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
     FAB
    -0.06
     lengthened
    -0.06
    হারে
    -0.06
    hmad
    -0.06
     psychological
    -0.06
     ड्रीम
    -0.06
     accidental
    -0.06
    +
    -0.06
    ือก
    -0.06
    channels
    -0.06
    POSITIVE LOGITS
     here
    0.07
     as
    0.06
     как
    0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
    ↵↵↵↵↵↵↵↵↵↵↵
    0.06
     संप
    0.06
    冷的
    0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
    ↵↵↵↵↵↵↵↵↵↵
    0.06
    Activations Density 0.003%

    No Known Activations