© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 48914
    Prev
    Next
    INDEX
    Explanations

    payments and financial transactions

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

    financial transactions and investment opportunities

    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_262k_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
    itochond
    0.54
     Erkrank
    0.52
    科学家
    0.51
     człowieka
    0.51
    人类
    0.50
    疾患
    0.50
     молеку
    0.47
    痙
    0.46
     ฮ
    0.46
     людини
    0.46
    POSITIVE LOGITS
     payment
    0.64
     wallets
    0.63
     tarifas
    0.61
     payments
    0.59
     prepaid
    0.57
     subscriptions
    0.56
     receivables
    0.55
     investors
    0.55
     postpaid
    0.55
     escrow
    0.55
    Activations Density 0.000%

    No Known Activations