© 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. 119929
    Prev
    Next
    INDEX
    Explanations

    medical terms, scientific papers, code documentation

    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
    Palest
    -0.06
     যেভাবে
    -0.06
     Palestinians
    -0.06
     arty
    -0.06
    egg
    -0.06
     часть
    -0.06
    Iran
    -0.06
    Seg
    -0.06
     caps
    -0.06
     ourselves
    -0.05
    POSITIVE LOGITS
     sequence
    0.06
     hypothetical
    0.06
     Б
    0.06
    sequence
    0.06
     supérieures
    0.06
     contienen
    0.06
     neutralized
    0.06
     दैनिक
    0.06
     DAILY
    0.06
     container
    0.06
    Activations Density 0.001%

    No Known Activations