© 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. 24003
    Prev
    Next
    INDEX
    Explanations

    meet and greet

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects instances of the word “Meet” used as a heading or intro line to introduce a person or entity.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     $
    -3.28
     
    -2.88
    ፨
    -2.80
     siguiente
    -2.56
     {
    -2.55
     \
    -2.55
     (
    -2.48
    chtenstein
    -2.47
    ing
    -2.38
    ⤥
    -2.36
    POSITIVE LOGITS
     火鍋
    3.25
     古风
    3.23
    kemeja
    3.02
    勠
    2.91
     باسلام
    2.91
     friv
    2.88
     夜景
    2.86
    
    2.86
    硨
    2.84
     merce
    2.83
    Activations Density 0.007%

    No Known Activations