© 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. 104767
    Prev
    Next
    INDEX
    Explanations

    Rah, Raul, Telerik, Monica

    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
     But
    -3.27
    '
    -3.13
    也可以
    -2.77
     y
    -2.77
    -2.75
     is
    -2.61
     这
    -2.53
     o
    -2.52
    -2.50
     The
    -2.48
    POSITIVE LOGITS
    婼
    3.23
    鹀
    3.19
    槩
    3.17
    actéristi
    3.11
    彞
    3.03
    𓆏
    2.91
     内衣
    2.83
    棪
    2.78
    婓
    2.75
    拊
    2.73
    Activations Density 0.002%

    No Known Activations