© 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. 13586
    Prev
    Next
    INDEX
    Explanations

    dollar amounts in billions

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

    billions and trillions

    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
     व्यक्तियों
    0.44
    分钟
    0.40
    工作人员
    0.39
    人数
    0.39
    itriangular
    0.39
    
    0.39
     Δ
    0.38
     अवधि
    0.38
    日数
    0.38
     현실
    0.37
    POSITIVE LOGITS
     billions
    0.73
     trillions
    0.63
     billion
    0.57
     milliard
    0.53
     Milliarden
    0.52
     ~$
    0.52
     investments
    0.51
     Billion
    0.51
     investimentos
    0.51
     miliardi
    0.51
    Activations Density 0.028%

    No Known Activations