© 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. 69063
    Prev
    Next
    INDEX
    Explanations

    lurking and lurching

    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
     剤
    -3.20
    玧
    -2.95
    鈰
    -2.77
    觔
    -2.70
    醅
    -2.66
     唯美
    -2.63
    獃
    -2.59
    趵
    -2.59
    鉭
    -2.58
     chevalier
    -2.55
    POSITIVE LOGITS
    '
    3.08
     "
    2.78
    AN
    2.66
     I
    2.63
     are
    2.47
    ON
    2.42
     
    2.41
     in
    2.41
     gutes
    2.30
     for
    2.28
    Activations Density 0.003%

    No Known Activations