© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32780
    Prev
    Next
    INDEX
    Explanations

    fresh seasonal local ingredients

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

    The neuron fires on descriptive terms highlighting food quality and provenance—words like “organic,” “fresh,” “seasonal,” and similar ingredient-quality markers.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    setContentView
    -1.29
    логе
    -1.24
    鸳
    -1.20
    Dichloroprop
    -1.17
     файлов
    -1.14
     artigo
    -1.12
     CONSUM
    -1.09
    ática
    -1.08
    useful
    -1.08
     aniversário
    -1.06
    POSITIVE LOGITS
     local
    1.72
     nearby
    1.49
     sources
    1.47
     lokale
    1.45
     fresh
    1.45
     from
    1.38
     freshness
    1.30
     мест
    1.25
     fresher
    1.24
     what
    1.21
    Activations Density 0.019%

    No Known Activations