© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49408
    Prev
    Next
    INDEX
    Explanations

    living room or area

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

    The neuron strongly activates on mentions of “living room” (and related room-name tokens like “dining room”), i.e. it detects references to living/dining room spaces.

    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
    Administrator
    -0.89
     женщины
    -0.79
    あー
    -0.78
     brilhante
    -0.77
    nings
    -0.76
     agradável
    -0.76
    inander
    -0.75
    ሁ
    -0.75
    inou
    -0.74
     ObjectParameter
    -0.74
    POSITIVE LOGITS
     room
    3.08
     Room
    2.53
    room
    2.45
     rooms
    2.11
    Room
    2.03
    rooms
    1.86
     ROOM
    1.84
    ROOM
    1.82
     Rooms
    1.60
     area
    1.59
    Activations Density 0.012%

    No Known Activations