© 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. 120854
    Prev
    Next
    INDEX
    Explanations

    code keywords and types

    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
     አ
    -0.06
    1
    -0.06
    Sand
    -0.05
    Smith
    -0.05
     tư
    -0.05
    Пере
    -0.05
    acek
    -0.05
     அருள்
    -0.05
    II
    -0.05
     ,"
    -0.05
    POSITIVE LOGITS
     sophisticated
    0.08
     प्रोत्साहन
    0.07
    Callories
    0.07
     by
    0.07
     notre
    0.07
    SubDirectoryPath
    0.07
     motto
    0.07
    ྙ
    0.07
     creates
    0.07
     અથવા
    0.07
    Activations Density 0.003%

    No Known Activations