© 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-262K
    7. 143325
    Prev
    Next
    INDEX
    Explanations

    Game of Thrones, British, justice, acidic

    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_262k_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
     egypt
    0.47
     jokes
    0.47
     aujourd
    0.43
    za
    0.43
     adverts
    0.43
     exploits
    0.42
    vä
    0.41
    此
    0.41
     ನಿಜ
    0.41
     locked
    0.41
    POSITIVE LOGITS
    螈
    0.52
     размера
    0.48
     размеров
    0.47
    产
    0.43
     দুটি
    0.41
    ্ি
    0.40
     కీల
    0.39
    룔
    0.39
     размер
    0.39
     حجم
    0.39
    Activations Density 0.018%

    No Known Activations