© 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. 115828
    Prev
    Next
    INDEX
    Explanations

    tear gas, pepper spray, variety of

    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
     některé
    -0.06
     przek
    -0.06
    要是
    -0.05
    繇
    -0.05
    darkMode
    -0.05
     rapidez
    -0.05
     befri
    -0.05
    atically
    -0.05
     Sarajevo
    -0.05
     মিডি
    -0.05
    POSITIVE LOGITS
    生產
    0.07
     생산
    0.07
     использования
    0.06
     사용
    0.06
     примене
    0.06
     fairly
    0.06
     infrequently
    0.06
     misrepresented
    0.06
     تولید
    0.06
     climates
    0.06
    Activations Density 0.008%

    No Known Activations