© 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. 116248
    Prev
    Next
    INDEX
    Explanations

    local recycling, religious services

    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
     combust
    -0.07
     béton
    -0.07
    窿
    -0.07
    🏗
    -0.06
     generate
    -0.06
    emetery
    -0.06
    generate
    -0.06
     بعنوان
    -0.06
     burgers
    -0.06
     সম্ভাব্য
    -0.06
    POSITIVE LOGITS
     coordinated
    0.08
     உரிய
    0.06
    習慣
    0.06
     incompatible
    0.06
     cultured
    0.06
    apple
    0.06
    Instructions
    0.06
     intolerance
    0.06
    习惯
    0.06
     packet
    0.06
    Activations Density 0.012%

    No Known Activations