© 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. 24055
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by verb

    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
     姆
    -1.58
    ⌵
    -1.52
    ｆ
    -1.50
     such
    -1.47
     镇
    -1.40
     PENNSYLVANIA
    -1.39
    
    -1.38
    ˒
    -1.38
    henge
    -1.38
    ید
    -1.37
    POSITIVE LOGITS
     to
    2.06
     $
    1.60
     
    1.57
     â
    1.53
     THE
    1.40
    において
    1.37
     ?
    1.34
     самая
    1.33
     \
    1.30
     '
    1.29
    Activations Density 0.061%

    No Known Activations