© 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. 22-GEMMASCOPE-RES-131K
    7. 25213
    Prev
    Next
    INDEX
    Explanations

    class of year or cohort

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

    The neuron strongly responds to mentions of class‐of year labels and other year/date numbers (e.g. “class of 2014,” “1995,” “2021,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     and
    -0.98
     شع
    -0.96
    export
    -0.96
     Playoffs
    -0.94
    lussen
    -0.93
    fatto
    -0.88
     взрос
    -0.88
     stanga
    -0.88
    position
    -0.87
     semana
    -0.85
    POSITIVE LOGITS
     who
    1.62
     that
    1.50
     cohort
    1.47
     there
    1.42
     those
    1.30
     whom
    1.26
     lớp
    1.17
     batch
    1.15
     Jahrgang
    1.14
     class
    1.13
    Activations Density 0.054%

    No Known Activations