© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 73769
    Prev
    Next
    INDEX
    Explanations

    building systems and health

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

    technical and scientific content related to building systems, environmental controls, and parameters.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    ugio
    -0.78
    vif
    -0.71
    SetState
    -0.69
    拍摄
    -0.69
     manteniendo
    -0.68
     fetish
    -0.68
    calli
    -0.68
    potion
    -0.68
    Odin
    -0.68
    Preserve
    -0.68
    POSITIVE LOGITS
     occupant
    1.20
     refrigerant
    1.03
     HVAC
    1.02
     Building
    1.00
     Occup
    0.98
     occupants
    0.98
     building
    0.97
     BAC
    0.96
    Occup
    0.90
     Buildings
    0.90
    Activations Density 0.011%

    No Known Activations