© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103528
    Prev
    Next
    INDEX
    Explanations

    numbers followed by mg

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

    The neuron activates on numeric tokens (i.e. sequences of digits), highlighting numbers such as dosages and measurements.

    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
     elbow
    -0.82
    듀
    -0.73
     gallons
    -0.73
     угло
    -0.73
     electricity
    -0.71
     cudd
    -0.69
    umus
    -0.69
     TextAppearance
    -0.69
     stop
    -0.68
    یشه
    -0.68
    POSITIVE LOGITS
     mg
    3.73
    mg
    3.31
     milligrams
    2.63
     MG
    2.38
     Mg
    2.27
    MG
    2.27
    Mg
    1.95
     мг
    1.67
    ㎎
    1.63
     mgr
    1.40
    Activations Density 0.082%

    No Known Activations