© 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. 43487
    Prev
    Next
    INDEX
    Explanations

    photographed by or in

    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
    的
    -3.36
    可以
    -2.95
    to
    -2.84
    想
    -2.75
    琑
    -2.73
    ra
    -2.64
    可
    -2.55
    是
    -2.52
    чка
    -2.50
    其他
    -2.47
    POSITIVE LOGITS
    汭
    3.42
    艄
    3.02
    姈
    2.84
    萑
    2.84
    箩
    2.81
    ↵
    2.72
    聍
    2.67
    を設置
    2.67
    酲
    2.67
    随即
    2.66
    Activations Density 0.040%

    No Known Activations