© 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. 118809
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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
    ,
    -0.07
    ร
    -0.06
     a
    -0.06
     за
    -0.06
     of
    -0.06
    lar
    -0.06
     așa
    -0.05
    elie
    -0.05
     my
    -0.05
     His
    -0.05
    POSITIVE LOGITS
     अधिकांश
    0.07
    ほとんど
    0.06
     begonnen
    0.06
     آن‌ها
    0.06
    скольку
    0.06
     начали
    0.06
     संबंधित
    0.06
    Xiv
    0.06
     ensuring
    0.06
     경찰
    0.06
    Activations Density 0.009%

    No Known Activations