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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 10693
    Prev
    Next
    INDEX
    Explanations

    foreign investment and business ventures

    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
    疗
    0.82
    预防
    0.76
    治疗
    0.74
     dragState
    0.72
     儿童
    0.70
    报警
    0.68
    人类
    0.67
    减轻
    0.66
    诅
    0.66
     théra
    0.64
    POSITIVE LOGITS
    business
    1.18
    投資
    1.18
     business
    1.16
     investment
    1.10
     investor
    1.07
    企業
    1.07
     investors
    1.05
     бизнес
    1.03
     BUSINESS
    1.01
     INVESTMENT
    1.00
    Activations Density 0.072%

    No Known Activations