© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68084
    Prev
    Next
    INDEX
    Explanations

    units of length

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

    The neuron detects numeric measurements—numbers (often with decimals) that quantify dimensions, distances, or units.

    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
     patienter
    -1.78
     varier
    -1.66
     étrang
    -1.66
     reparación
    -1.61
     fabricación
    -1.61
     vôtre
    -1.61
    ครื่อง
    -1.60
    とも言
    -1.56
     instalación
    -1.55
     déchir
    -1.54
    POSITIVE LOGITS
        
    2.03
         
    2.00
           
    1.92
             
    1.83
            
    1.83
          
    1.75
       
    1.63
      
    1.63
                 
    1.62
     .....
    1.59
    Activations Density 0.004%

    No Known Activations