© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21464
    Prev
    Next
    INDEX
    Explanations

    love with or again

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

    The neuron fires on expressions of love or being “in love” (strong affectionate language centered on the word “love”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    The
    -2.00
     cientos
    -1.98
    ((
    -1.98
    Its
    -1.91
     '-':
    -1.91
     the
    -1.88
     })}
    -1.88
     einem
    -1.85
    䜣
    -1.84
     でも
    -1.83
    POSITIVE LOGITS
    櫺
    2.17
    Также
    2.03
     emporio
    2.02
     etui
    1.98
    潆
    1.96
     Они
    1.95
     tecnico
    1.94
     elettrico
    1.89
     剧照
    1.87
     oock
    1.87
    Activations Density 0.003%

    No Known Activations