© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64616
    Prev
    Next
    INDEX
    Explanations

    romantic pursuit

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

    The neuron fires on words and phrases related to romantic courtship and dating (e.g. “romantic,” “love,” “suitor(s),” “courtship,” “flirt,” “dating,” “attraction”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     podí
    -0.82
    老公
    -0.81
    träge
    -0.81
    瘾
    -0.79
    ignant
    -0.79
     вагі
    -0.78
    izzera
    -0.77
    り返
    -0.77
    paravant
    -0.76
     Collabor
    -0.76
    POSITIVE LOGITS
     woo
    2.23
     courtship
    2.06
     courting
    2.02
     flirting
    1.59
     flirt
    1.55
     proposing
    1.45
     suitors
    1.45
     proposal
    1.45
     pursuit
    1.43
     pursue
    1.41
    Activations Density 0.044%

    No Known Activations