© 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. 36416
    Prev
    Next
    INDEX
    Explanations

    commerce and brands

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

    commerce and marketplaces

    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
     पहुंचकर
    0.44
    ımızı
    0.43
    amię
    0.43
     க்
    0.42
    meniz
    0.41
     Maternity
    0.41
    ų
    0.41
     Auditorium
    0.40
    ᴀ
    0.40
    ști
    0.40
    POSITIVE LOGITS
     ebay
    0.50
     prestigio
    0.47
     commerce
    0.47
     estoppel
    0.47
     mundo
    0.45
    Westinghouse
    0.44
     forums
    0.43
     world
    0.43
     market
    0.43
     reputation
    0.43
    Activations Density 0.001%

    No Known Activations