© 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. 79461
    Prev
    Next
    INDEX
    Explanations

    grams and grammes

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

    The neuron activates on numerical quantity tokens (measurements, counts, and unit values) in the text.

    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
    滷
    -0.86
     tâm
    -0.79
     trillion
    -0.77
    樁
    -0.77
     only
    -0.76
    ҵ
    -0.75
     condena
    -0.75
    東海
    -0.75
    pina
    -0.73
     班
    -0.73
    POSITIVE LOGITS
     grams
    1.61
     gram
    1.27
     weighing
    1.16
     weighed
    1.15
     quantity
    1.09
     Grams
    1.09
    grams
    1.06
     weigh
    1.05
    gram
    1.02
    amount
    1.02
    Activations Density 0.018%

    No Known Activations