© 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. 15206
    Prev
    Next
    INDEX
    Explanations

    company, bees, swarm

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

    company origin or subsidiary

    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
    现代
    0.44
    模拟
    0.44
     இன்
    0.44
     چې
    0.43
    脚本
    0.43
    是个
    0.43
    ꫝ
    0.43
    ɵ
    0.41
    提供的
    0.41
     Lur
    0.40
    POSITIVE LOGITS
    entreprise
    0.48
    AMSUNG
    0.47
     COMPANIES
    0.46
    기업
    0.43
     कम्पनी
    0.43
     salary
    0.43
     الشركات
    0.42
    회사
    0.42
    company
    0.41
     empresas
    0.41
    Activations Density 0.089%

    No Known Activations