© 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. 69522
    Prev
    Next
    INDEX
    Explanations

    iceberg, shippers, Skyrim, Ridley, Abrams, turrets

    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
    綃
    -3.45
     informar
    -3.06
    棪
    -2.97
    鋮
    -2.88
    (ﾟ
    -2.86
    鈇
    -2.86
     火鍋
    -2.83
     cristo
    -2.75
    (´
    -2.75
    其妙
    -2.73
    POSITIVE LOGITS
     i
    2.88
     <
    2.84
     
    2.83
     ???
    2.83
    <i>
    2.81
    "
    2.70
    有点
    2.70
    id
    2.67
    r
    2.67
    ing
    2.64
    Activations Density 0.012%

    No Known Activations