© 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. 109073
    Prev
    Next
    INDEX
    Explanations

    office and workplace spaces

    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
    sekolah
    -0.98
    ESSA
    -0.83
    rumah
    -0.82
    meteries
    -0.81
     hyperplasia
    -0.81
     lâm
    -0.80
    dwell
    -0.80
     retort
    -0.79
    roma
    -0.77
    eció
    -0.76
    POSITIVE LOGITS
     office
    2.80
     offices
    2.08
    office
    1.98
     Office
    1.86
     workplace
    1.80
     OFFICE
    1.78
     tenants
    1.72
     Offices
    1.66
    Office
    1.66
     tenant
    1.60
    Activations Density 0.034%

    No Known Activations