© 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. 128071
    Prev
    Next
    INDEX
    Explanations

    Q:, Genetic, Broker, Man

    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
     honors
    -0.07
     विज्ञान
    -0.07
     الحصول
    -0.07
    を得
    -0.07
     impractical
    -0.06
     futur
    -0.06
     honours
    -0.06
     basit
    -0.06
     Honours
    -0.06
    簡單
    -0.06
    POSITIVE LOGITS
    Ρ
    0.06
     scheduling
    0.06
     என்பவர்
    0.06
     таки
    0.06
     cannot
    0.05
     operative
    0.05
     accidentally
    0.05
     ____________
    0.05
     सोनू
    0.05
     ഉണ്ടാ
    0.05
    Activations Density 0.001%

    No Known Activations