© 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. 23749
    Prev
    Next
    INDEX
    Explanations

    business establishments and founders

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

    businesses and trade

    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
     nascetur
    0.46
     ataque
    0.44
     অজ্ঞাত
    0.42
     फसलों
    0.42
     yield
    0.42
    ależy
    0.41
    বিচার
    0.40
    𝜆
    0.40
     Yield
    0.40
     कुलपति
    0.39
    POSITIVE LOGITS
     shop
    0.71
     business
    0.68
     retailing
    0.68
    商店
    0.67
     магазине
    0.66
     negozio
    0.64
    本店
    0.64
     retail
    0.63
     firma
    0.63
     trading
    0.62
    Activations Density 0.055%

    No Known Activations