© 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. 117111
    Prev
    Next
    INDEX
    Explanations

    `doc/` files with license or descriptive text

    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
     எனப்படும்
    -0.07
     применяется
    -0.06
     membantu
    -0.06
     помогают
    -0.06
     ugly
    -0.06
     helps
    -0.06
    Tuple
    -0.06
     closely
    -0.06
     assisting
    -0.06
     aviation
    -0.06
    POSITIVE LOGITS
     Along
    0.07
     세상
    0.07
    選び
    0.07
     ২১
    0.07
     선정
    0.06
    selection
    0.06
     cerita
    0.06
     công
    0.06
    obiles
    0.06
    ื่อย
    0.06
    Activations Density 0.004%

    No Known Activations