© 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. 115899
    Prev
    Next
    INDEX
    Explanations

    US states

    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
     fancied
    -0.06
     ইন্ডাস্ট
    -0.06
     произво
    -0.06
    োন
    -0.06
    katapos
    -0.06
     তাদেরকে
    -0.06
     こんな
    -0.06
    ఐ
    -0.06
     inauguration
    -0.06
     comienzo
    -0.06
    POSITIVE LOGITS
     on
    0.06
    AM
    0.06
     with
    0.06
     බ
    0.05
    Larry
    0.05
    -
    0.05
    >>
    0.05
    However
    0.05
     while
    0.05
    With
    0.05
    Activations Density 0.005%

    No Known Activations