© 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. 84085
    Prev
    Next
    INDEX
    Explanations

    parking garage, ramp

    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
     chied
    -0.83
    mocked
    -0.82
    国道
    -0.77
     huevos
    -0.76
     helicopters
    -0.72
     bistro
    -0.71
     Krypto
    -0.71
     bbq
    -0.71
     Compt
    -0.71
     Medusa
    -0.70
    POSITIVE LOGITS
     garage
    2.36
     parking
    1.84
     garages
    1.77
     Garage
    1.66
    garage
    1.65
     underground
    1.64
     Parking
    1.54
     valet
    1.53
    Garage
    1.48
    parking
    1.31
    Activations Density 0.021%

    No Known Activations