© 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. 90937
    Prev
    Next
    INDEX
    Explanations

    paying attention

    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
    IsNullOrEmpty
    -0.84
    ické
    -0.77
    lup
    -0.75
    cá
    -0.75
     kiệm
    -0.74
    sigt
    -0.72
    キュリティ
    -0.72
    вою
    -0.71
     тер
    -0.71
    魄
    -0.70
    POSITIVE LOGITS
     paying
    4.69
     pay
    4.63
    Pay
    3.92
    pay
    3.75
     Pay
    3.73
    paying
    3.69
     pays
    3.66
     Paying
    3.55
    Paying
    3.39
     PAY
    3.28
    Activations Density 0.051%

    No Known Activations