© 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. 47359
    Prev
    Next
    INDEX
    Explanations

    fractional or quarter measurements

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

    The neuron primarily activates on numerical tokens and measurements (digits, fractions, and quantities).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    Manager
    -0.71
    зда
    -0.70
    ဘ
    -0.69
     peripheral
    -0.68
    Pep
    -0.68
    ABOUT
    -0.68
    large
    -0.67
    шено
    -0.66
     Seuss
    -0.66
    设
    -0.66
    POSITIVE LOGITS
     quarter
    2.83
     Quarter
    2.50
    Quarter
    2.31
    quarter
    2.20
     ¼
    1.90
     QUARTER
    1.81
     quarters
    1.70
     Quarters
    1.40
     Viertel
    1.38
    ¼
    1.27
    Activations Density 0.030%

    No Known Activations