© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 4590
    Prev
    Next
    INDEX
    Explanations

    United States, companies, cities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ต้อง
    0.40
     argu
    0.39
    Ethoxy
    0.39
    澼
    0.39
    她说
    0.39
     言
    0.39
     病
    0.39
     考え
    0.39
    罹
    0.39
    ründ
    0.38
    POSITIVE LOGITS
     United
    0.49
     Ltd
    0.46
    0
    0.44
     Walmart
    0.42
     LLC
    0.41
    -
    0.41
     alquiler
    0.41
     GmbH
    0.40
     estadounidense
    0.40
    ‌
    0.40
    Activations Density 0.023%

    No Known Activations