© 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. 99662
    Prev
    Next
    INDEX
    Explanations

    automation and lighting control

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

    The neuron fires on technical terms related to automated building control systems—especially HVAC, access control, and other facility‐automation vocabulary.

    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
    encu
    -0.87
    广大
    -0.85
    bower
    -0.85
    typeparam
    -0.82
    
    -0.77
    utando
    -0.76
     juiz
    -0.76
    突っ
    -0.75
    cant
    -0.75
     speedometer
    -0.75
    POSITIVE LOGITS
     lights
    1.30
     scene
    1.27
     scenes
    1.21
     away
    1.11
     automation
    1.09
     scenario
    1.09
     lighting
    1.07
     music
    1.01
     Away
    0.99
     Lights
    0.98
    Activations Density 0.021%

    No Known Activations