© 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. 114023
    Prev
    Next
    INDEX
    Explanations

    year ranges

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

    The neuron activates on four‐digit year tokens or year ranges (e.g. “1996–1999,” “2011–2012”), i.e. it identifies dates expressed as years.

    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
     or
    -2.31
     '
    -2.09
     
    -1.93
     and
    -1.88
     ''
    -1.78
     zwłaszcza
    -1.63
    b
    -1.62
    /
    -1.55
     especialmente
    -1.53
     szczególnie
    -1.51
    POSITIVE LOGITS
     produse
    1.62
     emporio
    1.55
    ________,
    1.49
    ílica
    1.47
    ülés
    1.45
     rire
    1.45
    ۱۹
    1.41
     手绘
    1.41
     batas
    1.40
     Prancis
    1.39
    Activations Density 0.080%

    No Known Activations