© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 11741
    Prev
    Next
    INDEX
    Explanations

    interest rate adjustments

    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_31_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
     выру
    0.52
    鉴定
    0.50
    燹
    0.50
     அழி
    0.49
    检测
    0.48
    质量
    0.48
     اسلح
    0.48
    物资
    0.47
    钣
    0.47
    爆发
    0.47
    POSITIVE LOGITS
     rates
    0.82
     Rates
    0.61
    利率
    0.61
     rate
    0.61
     RATES
    0.59
     दरों
    0.59
     mortgages
    0.57
    rates
    0.55
     lending
    0.52
     mortgage
    0.51
    Activations Density 0.054%

    No Known Activations