© 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. 36835
    Prev
    Next
    INDEX
    Explanations

    sales and products

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

    what you need

    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
    悆
    0.54
    胞
    0.49
    昃
    0.46
     Incorporated
    0.45
    區
    0.45
    णसी
    0.44
    ห
    0.44
    ამაშ
    0.43
    懐
    0.43
    shifting
    0.43
    POSITIVE LOGITS
     penjualan
    0.54
     Produkt
    0.47
    кров
    0.46
     produkt
    0.46
     vendedores
    0.45
     vendido
    0.44
     денег
    0.44
     Produktions
    0.44
     venta
    0.43
    ផ្គ
    0.43
    Activations Density 0.000%

    No Known Activations