© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129375
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    癌症
    -0.06
     may
    -0.06
     Weise
    -0.06
     gore
    -0.06
     bono
    -0.05
     decided
    -0.05
    FileURL
    -0.05
     philosophical
    -0.05
     могут
    -0.05
     sculptor
    -0.05
    POSITIVE LOGITS
    という
    0.08
     kenapa
    0.07
    なぜ
    0.07
     Porém
    0.06
    feels
    0.06
     보통
    0.06
     thân
    0.06
    璃
    0.06
    今後の
    0.06
     Provides
    0.06
    Activations Density 0.005%

    No Known Activations