© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 98467
    Prev
    Next
    INDEX
    Explanations

    bars, pubs, and inns

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

    The neuron detects references to drinking or dining establishments (e.g., pubs, bars, grills, inns, taverns).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     testator
    -1.14
     case
    -1.10
     grantor
    -1.09
     that
    -1.09
    tians
    -1.04
     varför
    -0.99
    4
    -0.97
     innym
    -0.96
     +
    -0.96
    which
    -0.96
    POSITIVE LOGITS
     restaurant
    1.73
     tavern
    1.34
    enangan
    1.19
    🍺
    1.16
     dining
    1.16
     景色
    1.16
     owner
    1.15
     alcoholic
    1.14
     atmosphere
    1.13
     alkoh
    1.13
    Activations Density 0.038%

    No Known Activations