© 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. 120970
    Prev
    Next
    INDEX
    Explanations

    running, trekking, question, ethurst

    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
     favoring
    -0.07
     emitted
    -0.07
     factorization
    -0.06
    刓
    -0.06
     simples
    -0.06
    false
    -0.06
     ovary
    -0.06
     सर्जरी
    -0.06
     verbessert
    -0.06
     favored
    -0.06
    POSITIVE LOGITS
     third
    0.06
     ۴
    0.06
     نیشنل
    0.06
     disponer
    0.06
     ´
    0.06
     an
    0.06
     ફરી
    0.05
     hemod
    0.05
     infrast
    0.05
     বিপর
    0.05
    Activations Density 0.002%

    No Known Activations