© 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. 92302
    Prev
    Next
    INDEX
    Explanations

    difference or distinction

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

    The neuron fires on occurrences of the word “difference” (and related phrases like “make all the difference” or “what’s the difference”).

    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
     folgendes
    -0.97
     intertwined
    -0.84
    paroles
    -0.83
    歓迎
    -0.79
     počet
    -0.77
    
    -0.77
     interconnected
    -0.77
     apostar
    -0.76
    sneaker
    -0.75
    吶
    -0.74
    POSITIVE LOGITS
     difference
    1.84
     the
    1.77
    Difference
    1.28
    difference
    1.26
     différence
    1.20
     Difference
    1.08
     diferença
    0.98
     diferencia
    0.98
     diferen
    0.93
     الفر
    0.93
    Activations Density 0.044%

    No Known Activations