© 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. 65820
    Prev
    Next
    INDEX
    Explanations

    seating and lounge areas

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

    The neuron is detecting mentions of seating or resting areas and related furniture (e.g. tables, chairs, sofas, lounges, resting zones).

    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
    ceries
    -0.82
    房間
    -0.82
    ษัท
    -0.82
     кухни
    -0.80
     buildings
    -0.79
     aeruginosa
    -0.77
    Mains
    -0.76
    走在
    -0.76
    ikyuu
    -0.75
     آباد
    -0.75
    POSITIVE LOGITS
     seating
    2.06
     lounge
    1.98
     relaxation
    1.64
     areas
    1.52
     sofas
    1.50
     couches
    1.49
     relax
    1.47
     Seating
    1.45
     Relaxation
    1.42
    relax
    1.40
    Activations Density 0.026%

    No Known Activations