© 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. 34-GEMMASCOPE-RES-131K
    7. 31898
    Prev
    Next
    INDEX
    Explanations

    quantities and ingredients

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

    This neuron detects numeric recipe quantities and measurements (e.g. ingredient amounts and units).

    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
     famí
    -0.99
    received
    -0.98
    ⎠
    -0.96
    toare
    -0.95
    сом
    -0.95
     geboren
    -0.94
     "'";
    -0.93
     PRET
    -0.91
    метри
    -0.91
     musée
    -0.90
    POSITIVE LOGITS
     salt
    1.20
     breadcrumbs
    1.09
     some
    1.09
     spices
    1.09
     herbs
    1.05
     then
    1.04
     milk
    1.03
     seasonings
    0.96
     plenty
    0.96
     lots
    0.95
    Activations Density 0.019%

    No Known Activations