© 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. 81029
    Prev
    Next
    INDEX
    Explanations

    land use and property

    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
     property
    -0.82
     Elector
    -0.82
     bootleg
    -0.81
     Simba
    -0.75
    bouncycastle
    -0.73
     pyram
    -0.73
     building
    -0.72
     homeowner
    -0.71
     buildings
    -0.70
    hata
    -0.70
    POSITIVE LOGITS
     allocation
    1.08
     allocations
    0.97
    lease
    0.96
     kyr
    0.91
     allocated
    0.90
     tenure
    0.89
     ceilings
    0.84
     ALLOC
    0.84
    gamepad
    0.80
     size
    0.79
    Activations Density 0.011%

    No Known Activations