© 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. 77468
    Prev
    Next
    INDEX
    Explanations

    love, passion, affinity for

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

    The neuron strongly activates on expressions of personal affection or enthusiasm—especially the word “love” (and related passions).

    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
    chers
    -0.95
    ်
    -0.83
    疗
    -0.81
     impide
    -0.81
    そこは
    -0.81
    Komentar
    -0.80
     contratar
    -0.79
     impresiones
    -0.78
    Zubereitung
    -0.77
     gms
    -0.76
    POSITIVE LOGITS
     for
    1.78
     of
    1.34
     and
    1.30
     towards
    1.10
     affair
    0.98
     affinity
    0.91
     toward
    0.91
     to
    0.88
     love
    0.84
     admiration
    0.83
    Activations Density 0.023%

    No Known Activations