© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 90657
    Prev
    Next
    INDEX
    Explanations

    tasting events and experiences

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

    This neuron fires on mentions of “tasting,” i.e. references to tasting events (wine, food, beer, etc.).

    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
    vosti
    -2.13
    chestra
    -2.06
    睺
    -2.02
    迓
    -1.98
    m
    -1.97
    ção
    -1.95
    yskland
    -1.95
    breviations
    -1.91
    тивные
    -1.91
    anians
    -1.84
    POSITIVE LOGITS
    ."
    2.16
    )
    2.05
    ("
    2.03
    ...(
    1.98
    Still
    1.98
    鉺
    1.98
    --"
    1.95
    :“
    1.86
     elegantly
    1.84
    B
    1.83
    Activations Density 0.005%

    No Known Activations