© 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. 34-GEMMASCOPE-RES-131K
    7. 90176
    Prev
    Next
    INDEX
    Explanations

    outdoor seating spaces

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

    The neuron activates for mentions of outdoor living spaces (e.g., decks, terraces, porches, patios).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     insides
    -0.90
     desejo
    -0.85
    pä
    -0.82
    ῃ
    -0.82
     розта
    -0.80
    metrist
    -0.80
    ByUsername
    -0.80
     befinden
    -0.78
     basement
    -0.77
    trale
    -0.77
    POSITIVE LOGITS
     overlooking
    1.25
     facing
    0.91
     outside
    0.88
    impinan
    0.84
     extending
    0.84
     planters
    0.83
    Diweddarwch
    0.83
    外面
    0.83
    cessed
    0.83
     seating
    0.83
    Activations Density 0.010%

    No Known Activations