© 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
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11446
    Prev
    Next
    INDEX
    Explanations

    names ending in ey or Hey

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

    greeting "hey"

    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_40_width_16k_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
     NRG
    0.41
     Neel
    0.38
    screen
    0.38
    ౖ
    0.38
    kT
    0.37
    significant
    0.37
     section
    0.37
    뀝
    0.37
    ̭
    0.36
    зже
    0.36
    POSITIVE LOGITS
     મળ
    0.49
    enschaft
    0.44
     hey
    0.43
    HEY
    0.42
    neys
    0.41
    Wey
    0.41
    
    0.39
    रां
    0.38
    Hey
    0.38
    ใช้งาน
    0.38
    Activations Density 0.189%

    No Known Activations