© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 105631
    Prev
    Next
    INDEX
    Explanations

    relax and unwind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    2
    -3.13
     Nachweis
    -2.88
    9
    -2.86
    お楽しみに
    -2.72
    3
    -2.69
    𖥧
    -2.67
    5
    -2.67
     Veränder
    -2.66
    4
    -2.66
    </h6>
    -2.59
    POSITIVE LOGITS
    🌼
    2.38
    🗿
    2.30
    ności
    2.23
    澳门
    2.19
    🌻
    2.17
    比如说
    2.17
    猫咪
    2.16
    👹
    2.16
    ！"
    2.13
    🤠
    2.13
    Activations Density 0.002%

    No Known Activations