© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47157
    Prev
    Next
    INDEX
    Explanations

    realtor real estate

    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
    Negative Logits
    liefer
    -0.93
     historien
    -0.76
    ensory
    -0.76
     demonio
    -0.75
     REGULAR
    -0.70
     customerId
    -0.69
     totiž
    -0.69
     във
    -0.68
    uluş
    -0.68
    Racing
    -0.68
    POSITIVE LOGITS
     real
    1.59
     brokerage
    1.50
     realty
    1.45
     broker
    1.44
     Realty
    1.41
     Broker
    1.38
     Real
    1.38
    Real
    1.36
     REAL
    1.32
     agent
    1.30
    Activations Density 0.024%

    No Known Activations