© 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. 124691
    Prev
    Next
    INDEX
    Explanations

    descending order or anatomical parts

    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
    as
    -2.88
    跄
    -2.64
    ak
    -2.61
    ta
    -2.44
    :"#
    -2.30
    y
    -2.28
     aspetta
    -2.28
    瑁
    -2.27
    褔
    -2.19
    ꜆
    -2.19
    POSITIVE LOGITS
    ↵
    3.81
    ଃ
    2.78
    目次
    2.67
    .'
    2.41
     搞笑
    2.36
    </em>
    2.31
    歃
    2.31
    除此之外
    2.30
     usw
    2.28
    昨年
    2.28
    Activations Density 0.003%

    No Known Activations