© 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. 98740
    Prev
    Next
    INDEX
    Explanations

    cloth and fabric textiles

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

    The main thing this neuron does is detect mentions of fabrics or textile materials.

    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
                    
    -1.54
        
    -1.54
                        
    -1.48
          
    -1.47
            
    -1.42
     does
    -1.35
              
    -1.34
    Награ
    -1.32
     However
    -1.32
    WRENCE
    -1.29
    POSITIVE LOGITS
    
    1.64
    }`;
    1.57
     เรา
    1.48
    ︲
    1.40
     ลูก
    1.40
     És
    1.38
     keď
    1.36
    皤
    1.34
    鸪
    1.32
     quando
    1.30
    Activations Density 0.065%

    No Known Activations