© 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. 65299
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by related nouns

    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
    了一个
    -2.44
     was
    -2.41
    cayaan
    -2.05
     includes
    -1.98
     wodurch
    -1.93
    一緒に
    -1.92
     zumal
    -1.91
     
    -1.89
     womit
    -1.88
    拊
    -1.85
    POSITIVE LOGITS
    Зміст
    2.22
     χρήση
    2.19
     través
    2.19
    
    2.17
    需要
    2.11
    дельник
    2.06
     навіть
    2.05
    medriver
    2.03
    ಝ
    2.02
    姍
    1.98
    Activations Density 0.027%

    No Known Activations