© 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. 45328
    Prev
    Next
    INDEX
    Explanations

    financial terms: assets, balance sheet, cash

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

    financial health and debt

    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
    ardı
    0.45
    输入的
    0.44
    关节
    0.42
     kalın
    0.41
    廪
    0.41
    主机
    0.41
    输出
    0.40
    实施
    0.40
    Telemetry
    0.40
    관
    0.40
    POSITIVE LOGITS
     indebtedness
    0.54
     borrowings
    0.54
     debts
    0.53
     debtors
    0.52
     cash
    0.52
     कर्ज
    0.50
     CASH
    0.49
     debtor
    0.49
     borrowers
    0.48
     Financing
    0.48
    Activations Density 0.049%

    No Known Activations