© 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. 63525
    Prev
    Next
    INDEX
    Explanations

    land and property records

    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
    ruitment
    -0.83
     informacija
    -0.83
     wedstrijd
    -0.79
     Zika
    -0.78
    LookAndFeel
    -0.75
     skla
    -0.74
     erhalten
    -0.73
     Medical
    -0.73
     лікар
    -0.73
     detract
    -0.72
    POSITIVE LOGITS
     land
    1.80
     parcels
    1.38
     property
    1.37
    Land
    1.35
     Land
    1.34
     parcel
    1.34
    parcel
    1.30
     Parcel
    1.20
     Property
    1.19
     cadast
    1.16
    Activations Density 0.015%

    No Known Activations