© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9125
    Prev
    Next
    INDEX
    Explanations

    is followed by descriptor

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

    The neuron strongly activates on the base forms of the linking verb “to be” (e.g. “is” and “are”).

    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
     &
    -2.34
     både
    -1.77
     but
    -1.65
    也会
    -1.64
    たちの
    -1.57
    并非
    -1.49
    也将
    -1.47
    にします
    -1.47
     etc
    -1.46
    他
    -1.46
    POSITIVE LOGITS
    </strong>
    1.79
    焢
    1.79
    atório
    1.78
     недвижимости
    1.74
        
    1.70
                                
    1.70
          
    1.67
              
    1.66
                  
    1.65
               
    1.63
    Activations Density 0.047%

    No Known Activations