© 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. 128113
    Prev
    Next
    INDEX
    Explanations

    number-based statistics

    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
    У
    -0.06
    我已经
    -0.06
     agora
    -0.06
     मिळाली
    -0.06
          
    -0.06
            
    -0.06
    ยน
    -0.05
     bénéf
    -0.05
    になっています
    -0.05
     tôi
    -0.05
    POSITIVE LOGITS
     especially
    0.08
     which
    0.07
     imbued
    0.07
     full
    0.07
     mostly
    0.06
     and
    0.06
     fully
    0.06
    ഷ്യ
    0.06
     approximately
    0.06
     tricky
    0.06
    Activations Density 0.042%

    No Known Activations