© 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. 117642
    Prev
    Next
    INDEX
    Explanations

    apartments and amenities

    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
     çanta
    -0.94
     зару
    -0.88
    mitter
    -0.83
     PUMP
    -0.83
    运转
    -0.81
    Spécification
    -0.79
    ご購入
    -0.77
    מוז
    -0.75
     歯科
    -0.75
    снаб
    -0.75
    POSITIVE LOGITS
     residents
    1.55
     apartment
    1.54
     apartments
    1.45
     leasing
    1.41
     community
    1.37
     Leasing
    1.32
     communities
    1.29
     Community
    1.27
     rent
    1.24
    Resident
    1.24
    Activations Density 0.017%

    No Known Activations