© 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. 42185
    Prev
    Next
    INDEX
    Explanations

    names of people and places

    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
     ‘
    -2.84
     
    -2.78
    来看看
    -2.58
     stirring
    -2.50
     stip
    -2.42
    <
    -2.42
    鼉
    -2.38
    _
    -2.36
    ⚣
    -2.34
    ized
    -2.33
    POSITIVE LOGITS
    envolvimento
    3.23
    嫗
    2.95
     itſelf
    2.91
     modificare
    2.78
     スケッチ
    2.77
    請繼續
    2.72
     Monfieur
    2.72
     fevere
    2.67
    ⢊
    2.61
     ツリー
    2.59
    Activations Density 0.067%

    No Known Activations