© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 45405
    Prev
    Next
    INDEX
    Explanations

    falling in love

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

    The neuron detects occurrences of the phrase “fall in love” (including its inflected forms like “fell in love,” “fallen in love,” and “falling in 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_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
     Aten
    -0.81
     Rela
    -0.75
     мали
    -0.75
     Quarte
    -0.74
    牡蠣
    -0.72
     ubicada
    -0.72
    FromNib
    -0.71
    APPROVED
    -0.70
     kendini
    -0.70
    らか
    -0.69
    POSITIVE LOGITS
     madly
    1.98
     in
    1.72
     enamorado
    1.58
     amoureux
    1.52
     innamor
    1.41
     enamor
    1.39
     apaixon
    1.38
     head
    1.16
    恋
    1.13
     IN
    1.11
    Activations Density 0.018%

    No Known Activations