© 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. 19862
    Prev
    Next
    INDEX
    Explanations

    Chromium Authors copyright

    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
    賸
    -2.88
    齶
    -2.75
     广告
    -2.47
    焿
    -2.47
    薷
    -2.39
    笮
    -2.38
     姜
    -2.34
    謌
    -2.34
    蘩
    -2.33
     foremost
    -2.28
    POSITIVE LOGITS
    ↵
    3.03
     ”
    2.47
    ,’”
    2.13
    寕
    2.09
     was
    2.02
     Перейти
    2.00
    形で
    2.00
     Küsten
    2.00
     for
    1.97
    inheritDoc
    1.95
    Activations Density 0.004%

    No Known Activations