© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 10500
    Prev
    Next
    INDEX
    Explanations

    Tinder swipes and carousels

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

    swipe, like, match

    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_31_width_262k_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
    ር
    0.47
     кня
    0.43
    Charset
    0.43
     darah
    0.43
    Domains
    0.42
     regiments
    0.42
    ኀ
    0.42
     informatics
    0.41
     porphy
    0.41
     domains
    0.41
    POSITIVE LOGITS
     Swipe
    0.82
    Swipe
    0.79
     swipes
    0.78
     swipe
    0.75
    swipe
    0.75
    carousel
    0.72
     Carousel
    0.69
    滑动
    0.68
     Tinder
    0.68
     滑
    0.68
    Activations Density 0.010%

    No Known Activations