© 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. 127917
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
     обстоятельства
    -0.05
     way
    -0.05
     भीषण
    -0.05
    might
    -0.05
     चांग
    -0.05
     Uptown
    -0.05
    Input
    -0.05
     input
    -0.05
    inn
    -0.05
    capital
    -0.05
    POSITIVE LOGITS
     یعنی
    0.06
    上記の
    0.06
    ಸ್ಪ
    0.06
    absence
    0.06
    یعنی
    0.06
     absence
    0.06
     نائب
    0.06
     치료
    0.06
    那种
    0.06
     лечения
    0.06
    Activations Density 0.012%

    No Known Activations