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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8115
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is detect numeric quantity and measurement expressions (e.g. amounts, units, and step numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    须
    0.66
    finished
    0.60
    add
    0.55
     تضيف
    0.55
    alal
    0.55
     trasporto
    0.54
     внесен
    0.54
    鑲
    0.54
     facades
    0.54
     memas
    0.53
    POSITIVE LOGITS
     tape
    0.85
     household
    0.75
     pliers
    0.69
     Tape
    0.66
     taped
    0.66
    household
    0.64
     paper
    0.62
    Tape
    0.62
     rulers
    0.61
     calculator
    0.60
    Activations Density 0.556%

    No Known Activations