© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48869
    Prev
    Next
    INDEX
    Explanations

    allure, lure, attraction, tempting offer

    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
     nguoi
    -0.88
    ジング
    -0.87
     éton
    -0.78
     Bekasi
    -0.78
    demia
    -0.77
     gaun
    -0.75
    inander
    -0.74
    áček
    -0.74
    lepiej
    -0.73
     diak
    -0.73
    POSITIVE LOGITS
     lure
    3.55
     tempting
    3.53
     enticing
    3.47
     attractive
    3.17
     allure
    3.06
     entice
    3.00
     tempt
    2.91
     lures
    2.91
     temptation
    2.86
     lured
    2.84
    Activations Density 0.098%

    No Known Activations