© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103772
    Prev
    Next
    INDEX
    Explanations

    negation of descriptions

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

    The neuron strongly activates on negation words—especially “not.”

    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
     on
    -2.17
     as
    -1.98
     intricacies
    -1.77
    In
    -1.77
     Really
    -1.66
     nuanced
    -1.66
    o
    -1.66
     by
    -1.65
     â
    -1.64
    𝗼
    -1.63
    POSITIVE LOGITS
     échanti
    1.98
    
    1.77
     kutu
    1.70
    gers
    1.66
     boîtes
    1.66
     ボーダー
    1.66
     obti
    1.64
    糁
    1.64
    
    1.64
     capucha
    1.63
    Activations Density 0.002%

    No Known Activations