© 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. 117261
    Prev
    Next
    INDEX
    Explanations

    Editor's notes and related phrases

    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
     and
    -0.09
    🍢
    -0.05
    ICLES
    -0.05
    要想
    -0.05
    如果要
    -0.05
    йович
    -0.05
     മുസ്‌
    -0.05
    roses
    -0.05
    [:]
    -0.05
     muốn
    -0.05
    POSITIVE LOGITS
     그러니까
    0.06
     inilah
    0.06
     ผ่าน
    0.06
     דר
    0.06
     related
    0.06
     บาง
    0.06
     दिग्
    0.05
     poumon
    0.05
     ત્રણ
    0.05
     czyli
    0.05
    Activations Density 0.003%

    No Known Activations