© 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. 27639
    Prev
    Next
    INDEX
    Explanations

    dating

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

    online dating profiles

    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
     hydrolysis
    0.51
     cylind
    0.49
     cilind
    0.47
     cylindrical
    0.46
     wept
    0.46
     archiv
    0.46
     destructive
    0.45
    継
    0.45
     цилинд
    0.44
     destruction
    0.44
    POSITIVE LOGITS
     Dating
    1.02
     dating
    0.84
     Tinder
    0.80
     flirting
    0.68
     रोमांटिक
    0.67
     matchmaking
    0.67
     meetup
    0.67
     Singles
    0.66
    dating
    0.65
    訕
    0.65
    Activations Density 0.105%

    No Known Activations