© 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. 120415
    Prev
    Next
    INDEX
    Explanations

    Inside init, Later lion, Somewhere if

    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
    ൩
    -0.07
    逑
    -0.06
     Typical
    -0.06
     바로
    -0.06
    clusively
    -0.06
     רק
    -0.06
    已有
    -0.06
     THEIR
    -0.06
    特征
    -0.06
    Typical
    -0.06
    POSITIVE LOGITS
     használ
    0.07
     destacó
    0.06
    ใส่
    0.06
     প্রতিরোধের
    0.06
     ejercicio
    0.06
     اتش
    0.06
    防水
    0.06
     Someone
    0.06
     अवि
    0.06
     استفاده
    0.06
    Activations Density 0.021%

    No Known Activations