© 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. 128142
    Prev
    Next
    INDEX
    Explanations

    .com

    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
     machen
    -0.06
     make
    -0.06
    ↑
    -0.06
     забра
    -0.06
     Horde
    -0.06
     Achieve
    -0.06
    เรื่อง
    -0.06
    表达
    -0.06
    を受ける
    -0.06
     이거
    -0.06
    POSITIVE LOGITS
     perhaps
    0.07
    perhaps
    0.07
     cunning
    0.06
     اخرى
    0.06
    另一种
    0.06
     another
    0.06
     somehow
    0.06
     adiabatic
    0.06
     أخرى
    0.06
     באופן
    0.06
    Activations Density 0.001%

    No Known Activations