© 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. 58279
    Prev
    Next
    INDEX
    Explanations

    at [organization/place/title]

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

    The neuron consistently activates on the preposition “at,” especially when it links a person or title to an organization.

    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
    皤
    -1.72
    ///////////////
    -1.54
     CERTAIN
    -1.48
    狴
    -1.46
    蓐
    -1.45
     "'";
    -1.44
     apret
    -1.43
     現貨
    -1.43
     klaar
    -1.41
    Berat
    -1.41
    POSITIVE LOGITS
         
    1.78
                   
    1.77
     of
    1.70
    //
    1.68
                         
    1.56
            
    1.56
                
    1.55
                    
    1.54
     +
    1.52
    A
    1.52
    Activations Density 0.012%

    No Known Activations