© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 3803
    Prev
    Next
    INDEX
    Explanations

    love of my life

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

    The neuron strongly activates on the phrase “love of” (i.e. expressions like “love of [something]”).

    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
    estimm
    -2.14
    '@
    -1.70
    koľ
    -1.65
     açúcar
    -1.56
     arbeta
    -1.51
    𓏸
    -1.51
    🩻
    -1.50
    ↝
    -1.48
     sabias
    -1.48
     and
    -1.48
    POSITIVE LOGITS
     associés
    1.60
    ır
    1.57
    out
    1.57
     eer
    1.49
    replyreport
    1.48
     In
    1.42
    们的
    1.41
     verstehen
    1.41
    zyć
    1.38
    ().
    1.37
    Activations Density 0.006%

    No Known Activations