© 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. 21839
    Prev
    Next
    INDEX
    Explanations

    connecting conjunctions and relative clauses

    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
     både
    -3.38
    ቷ
    -2.44
    桄
    -2.36
    
    -2.31
     også
    -2.22
    鴣
    -2.17
    先是
    -2.16
    瑧
    -2.14
     matematik
    -2.11
    珖
    -2.09
    POSITIVE LOGITS
    蔼
    3.09
     consequent
    2.77
    This
    2.61
    しました
    2.47
     eases
    2.39
    ية
    2.34
     Subsequent
    2.30
     Possibly
    2.30
    We
    2.27
     frankly
    2.13
    Activations Density 0.000%

    No Known Activations