© 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. 116775
    Prev
    Next
    INDEX
    Explanations

    code structure keywords like rust, SYS, perform

    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
    Not in Any Lists

    No Comments

    Negative Logits
     pics
    -0.06
     allowing
    -0.06
     obtain
    -0.06
     mortgagee
    -0.06
    ↵
    -0.06
    ැල
    -0.06
     ছবিতে
    -0.06
     bov
    -0.06
    、
    -0.06
    ),
    -0.05
    POSITIVE LOGITS
     bardzo
    0.07
     pokrač
    0.06
    很是
    0.06
     Sản
    0.06
     بسیار
    0.06
    因为它
    0.06
     wiele
    0.06
    MAG
    0.06
    ♑
    0.06
    ຮູ້
    0.06
    Activations Density 0.002%

    No Known Activations