© 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. 130609
    Prev
    Next
    INDEX
    Explanations

    staff member

    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
    同じ
    -0.07
     सीटेट
    -0.06
    會
    -0.06
    隊
    -0.06
     تعد
    -0.06
    我們會
    -0.06
    何を
    -0.06
    плат
    -0.06
     ఎక్కువ
    -0.06
    変更
    -0.05
    POSITIVE LOGITS
     of
    0.07
     wenn
    0.07
     beim
    0.06
     але
    0.06
     모습
    0.06
    ubjects
    0.06
     拉
    0.06
    0.05
     巴
    0.05
    Reception
    0.05
    Activations Density 0.014%

    No Known Activations