© 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. 119005
    Prev
    Next
    INDEX
    Explanations

    dependent on

    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
     '
    -3.03
    𓁹
    -2.77
    溏
    -2.75
    真剣
    -2.48
    ꜆
    -2.47
    ゆく
    -2.45
    秾
    -2.41
    屛
    -2.41
    МЫ
    -2.38
    价格
    -2.36
    POSITIVE LOGITS
    趼
    3.83
    because
    2.88
    沇
    2.86
    鋮
    2.83
    ～。
    2.81
    汭
    2.77
    翾
    2.77
    ～　
    2.73
    ୌ
    2.73
    ஂ
    2.72
    Activations Density 0.011%

    No Known Activations