© 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. 90590
    Prev
    Next
    INDEX
    Explanations

    Gson and droplets

    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
    -2.97
    '
    -2.50
    ⚋
    -2.33
    狃
    -2.25
    烔
    -2.14
    甚至
    -2.06
    Actually
    -2.06
    開始
    -2.06
    -2.06
    There
    -2.06
    POSITIVE LOGITS
     ヶ
    2.48
     ресни
    2.02
    之类的
    1.98
    “
    1.91
    侥
    1.91
    partements
    1.87
     redacción
    1.85
     atualmente
    1.84
    ⦊
    1.84
    嫆
    1.83
    Activations Density 0.002%

    No Known Activations