© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 6818
    Prev
    Next
    INDEX
    Explanations

    overwhelming positive/majority/evidence

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

    This neuron activates on the intensifier “overwhelming” (and its adverbial form), flagging strong emphasis on degree.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
            
    -2.58
                   
    -2.39
     There
    -2.27
                          
    -2.17
    可以
    -2.16
          
    -2.16
    (
    -2.14
                  
    -2.11
                 
    -2.09
                     
    -2.09
    POSITIVE LOGITS
    鸶
    2.11
    Ꭳ
    2.02
    踅
    1.96
    蕺
    1.95
    橚
    1.95
     geel
    1.94
    鹂
    1.94
    ة
    1.91
    릭터
    1.90
    ൎ
    1.88
    Activations Density 0.006%

    No Known Activations