© 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. 128055
    Prev
    Next
    INDEX
    Explanations

    information on or regarding

    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
     분류
    -0.06
     mentality
    -0.06
     clears
    -0.06
     worded
    -0.06
     classifies
    -0.06
     ኤ
    -0.06
     корректи
    -0.06
    dinga
    -0.06
     HIIT
    -0.06
     엄청
    -0.06
    POSITIVE LOGITS
     contrib
    0.06
     acontece
    0.05
     cic
    0.05
    ownie
    0.05
     юбилей
    0.05
     ensemble
    0.05
    LIBRARY
    0.05
    
    0.05
     contributions
    0.05
    want
    0.05
    Activations Density 0.014%

    No Known Activations