© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20659
    Prev
    Next
    INDEX
    Explanations

    indefinite articles ('a', 'an')

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

    The neuron activates on numeric expressions (integers and decimals) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    puestas
    -1.86
     to
    -1.78
    儛
    -1.73
     ۱۱
    -1.58
     utafiti
    -1.55
     which
    -1.50
     oyunu
    -1.48
     PROFES
    -1.46
     ۱۲
    -1.43
    踯
    -1.41
    POSITIVE LOGITS
     at
    1.81
     mismas
    1.79
     [
    1.77
     there
    1.61
     may
    1.55
     costumbres
    1.51
     ciertos
    1.37
     an
    1.36
     ofertas
    1.36
     two
    1.34
    Activations Density 0.070%

    No Known Activations