© 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. 127940
    Prev
    Next
    INDEX
    Explanations

    copyright and license headers

    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
     πρώ
    -0.07
     historique
    -0.07
     первым
    -0.07
     первая
    -0.07
     те
    -0.07
    同样
    -0.06
     stärker
    -0.06
     mistakenly
    -0.06
     پہلے
    -0.06
     columns
    -0.06
    POSITIVE LOGITS
       
    0.06
    मय
    0.06
    .
    0.05
      
    0.05
     bigotry
    0.05
    multiple
    0.05
    eye
    0.05
    ↵
    0.05
     ຈ
    0.05
    Multiple
    0.05
    Activations Density 0.001%

    No Known Activations