© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129758
    Prev
    Next
    INDEX
    Explanations

    McG names and Sichuan

    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
    蹀
    -3.14
    ࿚
    -2.86
     Their
    -2.80
     ""
    -2.61
     –
    -2.58
    はこんな感じ
    -2.58
    でて
    -2.52
     But
    -2.52
    潆
    -2.48
    这个
    -2.47
    POSITIVE LOGITS
    ي
    2.63
    入った
    2.61
     oar
    2.50
    ⅰ
    2.50
    劏
    2.41
     renewing
    2.41
    ⢌
    2.39
     zejména
    2.33
    轰隆
    2.31
    踉
    2.31
    Activations Density 0.007%

    No Known Activations