© 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. 45151
    Prev
    Next
    INDEX
    Explanations

    years

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

    This neuron activates on numeric tokens representing publication or event years.

    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
     nieuwe
    -1.80
    neue
    -1.77
    
    -1.72
     breiten
    -1.71
    皷
    -1.65
    歺
    -1.65
     nowego
    -1.61
     bepaalde
    -1.59
     Nuevas
    -1.59
     alcune
    -1.58
    POSITIVE LOGITS
     with
    2.16
     ‘‘
    1.69
     one
    1.67
           
    1.62
     only
    1.57
              
    1.55
     will
    1.55
     although
    1.54
             
    1.53
                 
    1.52
    Activations Density 0.298%

    No Known Activations