© 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. 110753
    Prev
    Next
    INDEX
    Explanations

    getaway

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

    The neuron detects mentions of leisure trips or vacations, specifically words like “getaway” and “retreat.”

    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
    厹
    -3.05
    猻
    -2.95
    趼
    -2.81
    ко
    -2.38
     anden
    -2.34
    塒
    -2.28
    銪
    -2.23
    噐
    -2.23
     aplikacji
    -2.23
    Is
    -2.23
    POSITIVE LOGITS
    ’
    2.92
     ‘
    2.80
     ‘‘
    2.55
     (‘
    2.53
     Moreover
    2.34
    龊
    2.34
     don
    2.33
    ,’
    2.31
     ‘’
    2.31
     According
    2.27
    Activations Density 0.003%

    No Known Activations