© 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. 73033
    Prev
    Next
    INDEX
    Explanations

    events continuing next

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

    The neuron activates on words that signal continuation or sequence—especially different forms of “continue” (continue, continues, continuing) and similar cue words like “next.”

    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
         
    -2.14
        
    -2.05
            
    -2.03
                       
    -1.80
       
    -1.78
           
    -1.78
                 
    -1.70
               
    -1.65
      
    -1.63
             
    -1.60
    POSITIVE LOGITS
    帮我
    1.69
    ᜀ
    1.59
     achet
    1.58
     vendus
    1.55
     bästa
    1.50
     детская
    1.45
    啊啊
    1.41
    mittag
    1.41
     dagar
    1.39
    unno
    1.38
    Activations Density 0.015%

    No Known Activations