© 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. 6681
    Prev
    Next
    INDEX
    Explanations

    positive emotions and emojis

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

    tentative connection and emotional development

    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
     recieved
    0.63
     atleast
    0.60
     recieve
    0.59
     leafs
    0.59
    됬
    0.59
    Anyways
    0.58
     Anyways
    0.57
    떄
    0.57
    非常に
    0.55
     anyways
    0.54
    POSITIVE LOGITS
    ❣️
    0.79
    🩷
    0.66
    ♥️
    0.61
    💕
    0.61
    ❤️
    0.59
    💞
    0.59
    ❤️❤️
    0.57
    💜
    0.57
    けれど
    0.57
    💗
    0.56
    Activations Density 0.141%

    No Known Activations