© 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. 31-GEMMASCOPE-2-RES-16K
    7. 14770
    Prev
    Next
    INDEX
    Explanations

    Christ, Father, Lord, life, death

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

    transaction commits gripper fracture conditions

    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_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
    赵
    0.40
    of
    0.39
    侦
    0.39
     Crazy
    0.39
     Immutable
    0.39
     STORE
    0.37
     uro
    0.37
    تم
    0.37
    떴
    0.37
    毽
    0.37
    POSITIVE LOGITS
    
    0.61
     акку
    0.54
    મેટ
    0.50
    harth
    0.48
     स्थिति
    0.48
     အတွ
    0.48
     Конгрегация
    0.47
    ný
    0.47
    သည်
    0.47
     encompass
    0.47
    Activations Density 0.011%

    No Known Activations