© 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. 10-GEMMASCOPE-RES-131K
    7. 105426
    Prev
    Next
    INDEX
    Explanations

    respect

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

    The neuron strongly activates on occurrences of the word “respect” (and its direct variants like “disrespect”).

    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
     aktuell
    -2.05
    郸
    -2.03
        
    -2.00
    liziert
    -1.86
    してた
    -1.84
     всем
    -1.81
    зм
    -1.80
    mpagne
    -1.79
         
    -1.77
     accuse
    -1.77
    POSITIVE LOGITS
    respect
    2.00
    鏵
    2.00
     simpel
    1.96
     maske
    1.95
    even
    1.87
     deri
    1.86
    镲
    1.80
    ໊
    1.76
     boks
    1.73
     jue
    1.71
    Activations Density 0.013%

    No Known Activations