© 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. 10-GEMMASCOPE-RES-131K
    7. 38490
    Prev
    Next
    INDEX
    Explanations

    meals and prices

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

    This neuron detects menu or meal‐section headings (e.g. “Mornings,” “Breakfast,” “Lunch”) and their associated scheduling or portion details in restaurant/menu descriptions.

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    licante
    -1.73
    aussian
    -1.66
     ungefär
    -1.61
    fizierung
    -1.58
     menyen
    -1.58
    oría
    -1.58
     kamb
    -1.55
     penger
    -1.51
    orship
    -1.51
    </sup>
    -1.51
    POSITIVE LOGITS
    镡
    1.74
    .
    1.69
     comprenant
    1.53
     competición
    1.52
     großes
    1.47
     composée
    1.43
     anderes
    1.42
     tradizione
    1.40
    decoración
    1.40
     weiteres
    1.39
    Activations Density 0.040%

    No Known Activations