© 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. 81587
    Prev
    Next
    INDEX
    Explanations

    real estate developers and properties

    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
     orgas
    -0.78
     pelt
    -0.77
    Mule
    -0.76
    のこと
    -0.75
     recor
    -0.75
     invented
    -0.75
    Apparatus
    -0.74
     delirium
    -0.71
    堺
    -0.70
     municip
    -0.69
    POSITIVE LOGITS
     developers
    0.90
     developer
    0.86
    🏠
    0.85
    properties
    0.85
     tenants
    0.84
     میلیارد
    0.81
    splan
    0.81
     menek
    0.81
     Developer
    0.80
    تری
    0.80
    Activations Density 0.005%

    No Known Activations