© 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. 7083
    Prev
    Next
    INDEX
    Explanations

    young people or youth

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

    LGBTQ youth

    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
    ghis
    0.40
    বিত্র
    0.38
    ༎
    0.38
    পৌ
    0.37
    醯
    0.36
    ollah
    0.34
    piej
    0.34
    uxe
    0.33
     মিসেস
    0.33
    LogLevel
    0.32
    POSITIVE LOGITS
     young
    4.72
    young
    4.56
    Young
    4.28
    年輕
    4.28
     YOUNG
    4.28
     젊
    4.22
    年轻
    4.19
     Young
    4.13
     joven
    4.13
     jovem
    4.13
    Activations Density 0.495%

    No Known Activations