© 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. 34-GEMMASCOPE-RES-131K
    7. 62565
    Prev
    Next
    INDEX
    Explanations

    Italian cities and history

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

    This neuron responds strongly to numeric tokens that form four-digit years (historical date markers).

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    toHaveBeen
    -0.74
    mui
    -0.73
     conclude
    -0.72
     McL
    -0.69
     ديسمبر
    -0.68
    Sid
    -0.68
     mere
    -0.66
    ธรรม
    -0.66
    Jack
    -0.65
     Breton
    -0.65
    POSITIVE LOGITS
     Turin
    1.84
     Torino
    1.62
     Piedmont
    1.58
    Torino
    1.45
     Juventus
    1.13
     Piemonte
    1.09
     Greensboro
    1.05
     Huddersfield
    0.96
    Pied
    0.95
     Grenoble
    0.94
    Activations Density 0.039%

    No Known Activations