© 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. 117449
    Prev
    Next
    INDEX
    Explanations

    retroviruses and viral infections

    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
     अरे
    -0.07
     combinaison
    -0.06
     مختلف
    -0.06
    第一时间
    -0.06
     लाइन
    -0.06
     acum
    -0.06
     વિવિધ
    -0.06
     distintos
    -0.06
    一個
    -0.06
    预计
    -0.06
    POSITIVE LOGITS
     Bishop
    0.07
    創作
    0.06
     เรา
    0.06
     вещи
    0.06
     枚
    0.05
    :)
    0.05
     творчества
    0.05
     cancers
    0.05
    ើយ
    0.05
    We
    0.05
    Activations Density 0.010%

    No Known Activations