© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11410
    Prev
    Next
    INDEX
    Explanations

    banking and accounts

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

    bank accounts and banking

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

    banking

    np_max-act · claude-4-5-sonnet
    Triggered by @sk5695

    banking

    np_max-act-logits · claude-4-5-sonnet
    Triggered by @sk5695
    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
    Negative Logits
    rüstung
    0.66
     CMake
    0.53
    ruppe
    0.50
     Discord
    0.50
    Webpack
    0.49
    gruppe
    0.49
     Diels
    0.48
    acés
    0.46
    箭头
    0.46
    诏
    0.46
    POSITIVE LOGITS
     banking
    1.70
     Banking
    1.64
    Banking
    1.57
    銀行
    1.52
     बैंकिंग
    1.52
     은행
    1.51
    banking
    1.50
     bank
    1.47
     bankers
    1.46
     Bankers
    1.41
    Activations Density 0.367%

    No Known Activations