© 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. 129932
    Prev
    Next
    INDEX
    Explanations

    .com websites announcing or describing Home/Health 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
    ي
    -0.07
     हमारा
    -0.06
     hätten
    -0.06
     저는
    -0.06
     there
    -0.06
     hatten
    -0.06
     сделали
    -0.06
     bunlar
    -0.06
     большая
    -0.06
     داشت
    -0.06
    POSITIVE LOGITS
    如下图
    0.07
     மட்டுமல்ல
    0.07
     đáp
    0.06
     腕時計
    0.06
    更に
    0.06
    乃至
    0.06
     மட்டு
    0.06
     EEUU
    0.06
     Judo
    0.06
     입니다
    0.06
    Activations Density 0.025%

    No Known Activations