© 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. 105843
    Prev
    Next
    INDEX
    Explanations

    exactly what why where how

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

    The neuron is specifically keyed to the adverb “exactly.”

    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
                 
    -1.73
     But
    -1.71
               
    -1.60
         
    -1.58
                   
    -1.55
              
    -1.55
                       
    -1.55
             
    -1.55
     in
    -1.54
            
    -1.53
    POSITIVE LOGITS
    淶
    1.86
    蕯
    1.77
     菇
    1.77
    婓
    1.77
    ꨄ
    1.68
     parlement
    1.65
     VIH
    1.65
    饜
    1.61
    nalités
    1.55
     boute
    1.54
    Activations Density 0.004%

    No Known Activations