© 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. 117740
    Prev
    Next
    INDEX
    Explanations

    mouse clicks or touch interaction

    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
     Holdings
    -0.06
    と思われる
    -0.05
    loom
    -0.05
     একট
    -0.05
    創新
    -0.05
    モダン
    -0.05
     innovation
    -0.05
    即
    -0.05
    Shir
    -0.05
     नॉट
    -0.05
    POSITIVE LOGITS
     ଯ
    0.06
     presently
    0.06
    ógico
    0.06
     مردم
    0.06
     प्रभारी
    0.06
    ตรวจ
    0.06
     現在
    0.06
    邀
    0.06
     проходи
    0.06
     Слова
    0.06
    Activations Density 0.004%

    No Known Activations