© 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. 120820
    Prev
    Next
    INDEX
    Explanations

    specific terms and definitions

    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
     logically
    -0.07
     consistency
    -0.06
     benchmark
    -0.06
     Consistency
    -0.06
     reference
    -0.06
     शोध
    -0.06
    Dealing
    -0.06
     review
    -0.06
    ಲಿ
    -0.06
     todo
    -0.06
    POSITIVE LOGITS
     endast
    0.06
    सामाजिक
    0.06
    unjungi
    0.06
    डीएम
    0.06
     ஊராட்சி
    0.06
     accompaniment
    0.06
     transformative
    0.06
    ментом
    0.05
     erzählt
    0.05
    щении
    0.05
    Activations Density 0.006%

    No Known Activations