© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47808
    Prev
    Next
    INDEX
    Explanations

    quantities of pounds

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

    The main thing this neuron does is detect numeric quantity tokens (e.g. weights, measurements, and other numbers).

    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
     conifers
    -0.85
    表記
    -0.82
    meter
    -0.80
     sml
    -0.79
     bitumen
    -0.79
    meters
    -0.76
     Merkel
    -0.76
     meters
    -0.74
    zęd
    -0.74
    Spenden
    -0.73
    POSITIVE LOGITS
     pounds
    2.11
     lbs
    1.72
     pound
    1.64
    lbs
    1.50
     lb
    1.49
     Pounds
    1.27
    pounds
    1.21
    lb
    1.19
    pound
    1.19
    磅
    1.03
    Activations Density 0.016%

    No Known Activations