© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118803
    Prev
    Next
    INDEX
    Explanations

    numbers or digits

    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
    ฝึก
    -0.06
     arbeitet
    -0.06
     acta
    -0.06
     পিতার
    -0.06
     moeder
    -0.06
     ܗܘ
    -0.06
    ຫຼື
    -0.06
     economists
    -0.06
     Aydın
    -0.06
     mismo
    -0.06
    POSITIVE LOGITS
    <0xE3>
    0.07
    ?.
    0.06
     صحی
    0.06
    ↵↵↵
    0.06
                
    0.06
     змен
    0.06
    લું
    0.06
     প্রদান
    0.05
     אני
    0.05
     умень
    0.05
    Activations Density 0.005%

    No Known Activations