© 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. 118298
    Prev
    Next
    INDEX
    Explanations

    LR moment

    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
    通过
    -0.06
    چم
    -0.06
    というか
    -0.06
    在她
    -0.06
     вернуться
    -0.06
     område
    -0.06
     через
    -0.06
    地區
    -0.06
     opět
    -0.06
     गड
    -0.06
    POSITIVE LOGITS
     daunting
    0.06
     ஆகியவை
    0.06
     siis
    0.06
    maa
    0.06
     Ведь
    0.06
    反复
    0.06
     ഏറെ
    0.06
     née
    0.05
    ↵↵
    0.05
     করবার
    0.05
    Activations Density 0.029%

    No Known Activations