© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15824
    Prev
    Next
    INDEX
    Explanations

    oil prices and energy industries

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

    oil, gas, prices, investment

    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_16k_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
     车
    0.59
    机器
    0.54
    机器人
    0.54
    钵
    0.52
    枫
    0.51
     Motorcycle
    0.50
    表达
    0.49
     Robot
    0.48
    辗
    0.48
     红
    0.48
    POSITIVE LOGITS
     oil
    1.40
    油
    1.36
    OIL
    1.32
     OIL
    1.30
    oil
    1.28
    Oil
    1.27
     minyak
    1.23
     Oil
    1.23
    石油
    1.23
    オイル
    1.21
    Activations Density 0.206%

    No Known Activations