© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 38867
    Prev
    Next
    INDEX
    Explanations

    first-past-the-post election system

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

    The neuron spotlights idiomatic “first”‐based phrases indicating order or priority—e.g. “first-come, first-serve” or “first-past-the-post.”

    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
      
    -1.80
            
    -1.76
     なら
    -1.71
    颔
    -1.67
              
    -1.62
    According
    -1.62
           
    -1.57
                    
    -1.53
     если
    -1.52
    Ẳ
    -1.51
    POSITIVE LOGITS
     for
    1.65
    pří
    1.64
    zoeken
    1.64
     inscripción
    1.63
     ejecución
    1.63
    dė
    1.55
     bañera
    1.52
    liegenden
    1.48
     transparencia
    1.48
     personalización
    1.48
    Activations Density 0.009%

    No Known Activations