© 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. 26311
    Prev
    Next
    INDEX
    Explanations

    Mughal emperors and their constructions

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

    ground colors

    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
    蕈
    0.45
    omyel
    0.45
     текста
    0.44
    iesis
    0.44
    otipi
    0.43
    ⵍ
    0.43
    izion
    0.42
    Ⲉ
    0.42
     можливо
    0.42
    ではありません
    0.41
    POSITIVE LOGITS
     france
    0.43
     Vogue
    0.43
     Froome
    0.43
     Drought
    0.42
     Jade
    0.42
     erhö
    0.41
     khiến
    0.40
     Density
    0.40
     giảm
    0.40
     Swo
    0.39
    Activations Density 0.003%

    No Known Activations