© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67166
    Prev
    Next
    INDEX
    Explanations

    computer context

    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
     enorme
    -2.50
    姐妹
    -2.47
    甃
    -2.41
    有点
    -2.38
    칵
    -2.38
    ’
    -2.34
     manque
    -2.34
    意大利
    -2.31
     
    -2.30
    尤其
    -2.23
    POSITIVE LOGITS
    ۹
    3.08
    ۵
    2.92
    ۷
    2.64
    緜
    2.61
    拍了拍
    2.61
    an
    2.58
    <em>
    2.58
    幾天
    2.55
    ۲
    2.55
     ответить
    2.52
    Activations Density 0.027%

    No Known Activations