© 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. 10-GEMMASCOPE-RES-131K
    7. 105666
    Prev
    Next
    INDEX
    Explanations

    multiplicity and multiplicative concepts

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

    This neuron activates on occurrences of the word “multiplicity.”

    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
    蹰
    -2.80
     encuentras
    -2.23
    zmm
    -2.22
     it
    -2.20
     distintas
    -2.06
    egd
    -2.05
     stesso
    -1.95
     proportions
    -1.94
    wyl
    -1.94
     腕
    -1.91
    POSITIVE LOGITS
    n
    3.50
    ated
    2.81
    4
    2.80
    i
    2.73
    ["
    2.66
    ities
    2.59
    0
    2.53
    6
    2.50
    ’
    2.48
    e
    2.41
    Activations Density 0.003%

    No Known Activations