© 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. 5350
    Prev
    Next
    INDEX
    Explanations

    San Diego

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

    dial, dice, die

    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
     აღმასრულ
    0.36
    ophagy
    0.35
    ចប់
    0.35
    臻
    0.34
    年月日
    0.33
    
    0.33
     स्लाइड्स
    0.33
     denaturation
    0.33
     jaguar
    0.33
     وده
    0.33
    POSITIVE LOGITS
     Ди
    2.69
     ди
    2.63
     dí
    2.50
     디
    2.48
    ディ
    2.45
    Ди
    2.45
     די
    2.39
    Dix
    2.39
     Diego
    2.36
    디
    2.36
    Activations Density 0.355%

    No Known Activations