© 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. 115883
    Prev
    Next
    INDEX
    Explanations

    barcode reader and plate recognition

    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
    sent
    -0.07
     keepsake
    -0.06
    打电话
    -0.06
    تا
    -0.06
     pinpoint
    -0.06
     vividly
    -0.06
     lokalen
    -0.06
     impede
    -0.06
    ್
    -0.06
    Про
    -0.06
    POSITIVE LOGITS
    combinations
    0.07
     combinations
    0.06
     комбина
    0.06
     speed
    0.06
     fler
    0.06
     সামনে
    0.06
    combine
    0.06
     Fastest
    0.05
     selections
    0.05
     T
    0.05
    Activations Density 0.006%

    No Known Activations