© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 3980
    Prev
    Next
    INDEX
    Explanations

    computation of interest and loans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    国防
    0.52
    行动
    0.51
     Membranes
    0.50
     മനുഷ്യ
    0.48
     réussir
    0.48
     profondes
    0.47
    人类
    0.47
    剑
    0.47
    严肃
    0.46
     تیم
    0.46
    POSITIVE LOGITS
     interest
    1.18
     Interest
    1.12
    interest
    1.09
    Interest
    1.07
     loan
    1.06
     ब्याज
    0.96
     loans
    0.93
     Loan
    0.91
     lãi
    0.91
     INTEREST
    0.88
    Activations Density 0.104%

    No Known Activations