© 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. 34-GEMMASCOPE-RES-131K
    7. 563
    Prev
    Next
    INDEX
    Explanations

    copyright statements and code headers

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

    The neuron is primarily activated by numeric digits (individual numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     OnEnable
    -0.86
    iligt
    -0.85
     affinity
    -0.84
    ulur
    -0.78
    Getenv
    -0.73
    invert
    -0.73
    ocardi
    -0.71
    matcher
    -0.70
    OLAR
    -0.70
    tacte
    -0.70
    POSITIVE LOGITS
         
    1.06
       
    0.96
      
    0.91
        
    0.90
                                 
    0.85
                 
    0.84
                                  
    0.81
                                
    0.80
     FCS
    0.80
    諒
    0.79
    Activations Density 0.104%

    No Known Activations