© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15597
    Prev
    Next
    INDEX
    Explanations

    paying attention, money, or debt

    np_acts-logits-general · gemini-2.5-flash-lite

    paying attention or money

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ર
    0.68
    bdd
    0.61
    savings
    0.61
    া
    0.61
    ből
    0.60
     trock
    0.59
    arı
    0.58
    smanship
    0.58
     undercut
    0.57
    a
    0.57
    POSITIVE LOGITS
    Paying
    0.86
    Paid
    0.82
     paid
    0.80
    Pay
    0.77
     homage
    0.75
    Pays
    0.75
    pays
    0.73
    pay
    0.71
     pays
    0.71
     pay
    0.70
    Activations Density 0.168%

    No Known Activations