© 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. 10-GEMMASCOPE-RES-131K
    7. 1817
    Prev
    Next
    INDEX
    Explanations

    positive emotions and relationships

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

    The neuron responds to strongly emotional, affect-laden words (e.g. grief, loss, love, compassion, heart, prayers).

    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
     sementes
    -1.64
    umumkan
    -1.53
    ungkapkan
    -1.50
    chalet
    -1.48
     Divulgação
    -1.41
    hadapi
    -1.40
    因為
    -1.39
    klare
    -1.38
    dne
    -1.38
    dapat
    -1.38
    POSITIVE LOGITS
     and
    1.84
    t
    1.81
     this
    1.71
     each
    1.71
     all
    1.63
     even
    1.63
    ers
    1.58
     has
    1.45
    os
    1.42
    y
    1.42
    Activations Density 0.052%

    No Known Activations