© 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. 72961
    Prev
    Next
    INDEX
    Explanations

    symbols in mathematical expressions

    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
     enticing
    -2.61
     unrelenting
    -2.58
     lustrous
    -2.53
    鸰
    -2.39
     ostensibly
    -2.38
     unwavering
    -2.27
    娛
    -2.23
    蒹
    -2.22
     sparkly
    -2.20
     exquisitely
    -2.20
    POSITIVE LOGITS
    咴
    3.58
    葙
    2.69
     イラストレーション
    2.66
    踮
    2.56
    苤
    2.55
    鬟
    2.52
    ,.
    2.44
    ;,
    2.42
    𐀀
    2.42
    咵
    2.39
    Activations Density 0.012%

    No Known Activations