© 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. 26583
    Prev
    Next
    INDEX
    Explanations

    financing

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

    loans, mortgages, financing

    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
    家伙
    0.53
    ğlu
    0.52
     دنی
    0.51
     팀
    0.51
    ampaikan
    0.50
    家长
    0.50
    ıza
    0.50
     निष्कर्ष
    0.50
     长
    0.49
    arlı
    0.49
    POSITIVE LOGITS
     loans
    0.79
     mortgages
    0.75
     loan
    0.74
     mortgage
    0.69
     financing
    0.68
     mortgagee
    0.68
     borrowers
    0.64
    貸款
    0.64
     borrower
    0.64
     lender
    0.64
    Activations Density 0.000%

    No Known Activations