© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 827
    Prev
    Next
    INDEX
    Explanations

    star performer or leader

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

    leading position or benchmark

    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_53_width_65k_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
     elaborate
    0.42
     elaborated
    0.38
    楽しく
    0.37
     basit
    0.37
    辟
    0.37
     낮은
    0.36
     elaboration
    0.36
     omfatt
    0.35
    简单的
    0.35
    넓
    0.35
    POSITIVE LOGITS
     superstar
    1.70
     superstars
    1.66
     powerhouse
    1.40
     titans
    1.36
     champion
    1.34
     सुपरस्टार
    1.34
     hero
    1.33
     champions
    1.33
     heroes
    1.31
     leader
    1.28
    Activations Density 0.569%

    No Known Activations