© 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. 120793
    Prev
    Next
    INDEX
    Explanations

    class `extends` or `topic` lists

    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
    Not in Any Lists

    No Comments

    Negative Logits
     first
    -0.07
     jeweil
    -0.06
     deriving
    -0.06
     নেতাকর্ম
    -0.06
     discernible
    -0.06
     Belg
    -0.06
     további
    -0.06
    ীয়
    -0.06
     ulteriori
    -0.06
    म्
    -0.05
    POSITIVE LOGITS
     उन्नत
    0.06
    ด้วย
    0.06
    jade
    0.06
     संकेत
    0.06
     bằng
    0.06
     ziemlich
    0.06
     owner
    0.06
    owner
    0.06
     quando
    0.06
     numeral
    0.06
    Activations Density 0.012%

    No Known Activations