© 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. 128596
    Prev
    Next
    INDEX
    Explanations

    css selectors or declarations

    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
     by
    -0.08
     empezar
    -0.08
     in
    -0.08
     什么
    -0.06
     대부분
    -0.06
     for
    -0.06
    开始
    -0.06
    旬
    -0.06
     with
    -0.06
     শুরু
    -0.06
    POSITIVE LOGITS
     trotz
    0.07
     vieja
    0.06
     വലിയ
    0.06
    oltre
    0.06
     определенных
    0.06
     ciertos
    0.06
     тощо
    0.06
     ছাড়াও
    0.06
     francia
    0.06
     Kepala
    0.06
    Activations Density 0.007%

    No Known Activations