© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6937
    Prev
    Next
    INDEX
    Explanations

    Forever Alone or dating

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

    The neuron fires on promotional, call-to-action advertising language—e.g. text pitching memberships, free accounts, or services.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_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
     നടപ
    0.61
     cường
    0.60
     choral
    0.59
     inco
    0.58
     mottled
    0.58
     insulators
    0.56
     تجهیز
    0.55
    굉
    0.55
    ruction
    0.54
     coherent
    0.54
    POSITIVE LOGITS
     Dating
    1.95
     dating
    1.87
     matchmaking
    1.76
    dating
    1.75
     Tinder
    1.68
     flirting
    1.49
     flirt
    1.41
    恋爱
    1.38
     Singles
    1.37
     courtship
    1.37
    Activations Density 0.502%

    No Known Activations