© 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. 120965
    Prev
    Next
    INDEX
    Explanations

    Three years

    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
     করোনায়
    -0.07
     უფრო
    -0.06
    军队
    -0.06
     ಅವನ
    -0.06
     از
    -0.06
     मुझसे
    -0.06
     splend
    -0.06
     noteworthy
    -0.06
     fontos
    -0.06
     явля
    -0.06
    POSITIVE LOGITS
     
    0.06
     instantiation
    0.06
    にい
    0.05
     To
    0.05
     what
    0.05
     прошли
    0.05
     来
    0.05
     insuffisamment
    0.05
    To
    0.05
     tibi
    0.05
    Activations Density 0.006%

    No Known Activations