© 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. 110891
    Prev
    Next
    INDEX
    Explanations

    occupancy, living, inhabitation

    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
     hùng
    -0.98
    typeparam
    -0.97
     backstage
    -0.94
    arschu
    -0.91
    isc
    -0.88
    omel
    -0.86
    向了
    -0.86
     handheld
    -0.85
    教室
    -0.85
    classroom
    -0.85
    POSITIVE LOGITS
     occupancy
    1.89
     occupants
    1.80
     living
    1.67
    Occup
    1.47
    住
    1.46
     inhabit
    1.45
     renovations
    1.41
    occup
    1.41
     lived
    1.40
     occupant
    1.34
    Activations Density 0.052%

    No Known Activations