© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 118615
    Prev
    Next
    INDEX
    Explanations

    footballer or football coach

    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
    더
    -0.06
     if
    -0.06
     damp
    -0.06
    一是
    -0.05
    aar
    -0.05
    ⚠️
    -0.05
    ดย
    -0.05
    irp
    -0.05
     can
    -0.05
    📕
    -0.05
    POSITIVE LOGITS
     ಇತರ
    0.06
     今天
    0.06
     உட்பட
    0.06
     різних
    0.06
     எண்ணிக்க
    0.06
     těchto
    0.06
     различни
    0.06
     Sehingga
    0.06
     цих
    0.06
    များနှင့်
    0.06
    Activations Density 0.023%

    No Known Activations