© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3017
    Prev
    Next
    INDEX
    Explanations

    real estate 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
    せない
    -0.76
     dinero
    -0.76
    ductor
    -0.75
    qrstuvwxyz
    -0.74
    unhofer
    -0.73
    ǣ
    -0.73
    ਾਲ
    -0.70
     थ
    -0.68
    Resource
    -0.68
    
    -0.67
    POSITIVE LOGITS
     property
    3.72
     properties
    2.86
    property
    2.67
     Property
    2.45
    Property
    2.36
     real
    2.25
    PROPERTY
    2.19
     PROPERTY
    2.16
     housing
    2.11
     Properties
    2.08
    Activations Density 0.046%

    No Known Activations