© 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. 53-GEMMASCOPE-2-RES-65K
    7. 2949
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ဆက်
    0.40
     चरम
    0.35
    銖
    0.35
    द्र
    0.35
    驽
    0.34
    癫
    0.34
     ++;
    0.33
     đột
    0.33
    聩
    0.33
    तंत्र
    0.33
    POSITIVE LOGITS
     beautiful
    4.50
    beautiful
    4.22
     Beautiful
    4.03
    Beautiful
    3.95
     краси
    3.80
     gorgeous
    3.63
     아름
    3.63
    美しい
    3.61
     krás
    3.55
     красивые
    3.55
    Activations Density 0.702%

    No Known Activations