© 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. 103650
    Prev
    Next
    INDEX
    Explanations

    local products and produce

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

    The main thing this neuron does is find mentions of local or regional products and food-related markets or producers.

    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
    ּוֹ
    -1.51
     patrie
    -1.27
     fazenda
    -1.24
    ConstraintSet
    -1.23
     praia
    -1.17
     an
    -1.17
     equipe
    -1.16
     grotte
    -1.15
     chocolat
    -1.14
     cerim
    -1.14
    POSITIVE LOGITS
    really
    1.45
    without
    1.37
    usually
    1.29
    almost
    1.24
    every
    1.24
     "",
    1.23
    纷纷
    1.22
    both
    1.20
    äs
    1.20
    AMERICAN
    1.19
    Activations Density 0.036%

    No Known Activations