© 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. 116236
    Prev
    Next
    INDEX
    Explanations

    guided biliary drainage, needle aspiration

    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
     caused
    -0.06
     because
    -0.06
     occasionally
    -0.06
    caused
    -0.06
    kata
    -0.05
     চালান
    -0.05
     प्रांत
    -0.05
    地區
    -0.05
     retorn
    -0.05
     reversal
    -0.05
    POSITIVE LOGITS
     ఇవ్వ
    0.07
     Blogging
    0.07
     डाइट
    0.07
    段階
    0.06
    ण्डे
    0.06
     LOST
    0.06
    ḵ
    0.06
     Emails
    0.06
     것은
    0.06
    ımız
    0.06
    Activations Density 0.013%

    No Known Activations