© 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. 75747
    Prev
    Next
    INDEX
    Explanations

    serving quantities and titles

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

    The neuron mainly detects numeric quantity mentions—tokens representing numbers, servings, measurements, or other numeric data.

    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
    platz
    -0.82
    chanter
    -0.80
    диод
    -0.80
    рус
    -0.77
     onBind
    -0.76
    дли
    -0.75
    simpleType
    -0.74
    asana
    -0.74
    znego
    -0.73
     Mawr
    -0.73
    POSITIVE LOGITS
     servings
    1.97
     serving
    1.50
     daily
    1.48
     fruit
    1.28
    serving
    1.22
     recommended
    1.21
     Serving
    1.11
     fruits
    1.05
    Serving
    1.05
    daily
    1.04
    Activations Density 0.034%

    No Known Activations