© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102919
    Prev
    Next
    INDEX
    Explanations

    android activity layouts

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

    the word "activity" in Android development contexts, particularly in layout and code file references.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron detects Android-specific identifiers—particularly resource filenames (e.g. “apk”, “activity_…”) and component/class names like “Activity” or “Fragment.”

    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
    饧
    -1.55
     Ши
    -1.55
     universidades
    -1.52
    strSql
    -1.51
     mereka
    -1.46
    农业
    -1.45
     países
    -1.45
     definitively
    -1.45
    ünden
    -1.44
     Vereinigten
    -1.40
    POSITIVE LOGITS
              
    2.09
                      
    1.91
          
    1.90
        
    1.89
         
    1.84
                
    1.84
                                
    1.81
               
    1.79
                        
    1.77
                 
    1.76
    Activations Density 0.018%

    No Known Activations