© 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. 84449
    Prev
    Next
    INDEX
    Explanations

    climate control systems ventilation heating defrosting

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Gastro
    -0.81
     getRule
    -0.79
    UPS
    -0.75
    ceum
    -0.75
    GAMES
    -0.75
    箸
    -0.75
    Straße
    -0.75
    chetti
    -0.74
     AppBar
    -0.73
     Niet
    -0.73
    POSITIVE LOGITS
     blower
    1.59
     defrost
    1.31
     cabin
    1.30
     heater
    1.30
     climate
    1.30
     vents
    1.21
     Cabin
    1.20
     Climate
    1.16
     blowing
    1.15
    Climate
    1.09
    Activations Density 0.012%

    No Known Activations