© 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. 83404
    Prev
    Next
    INDEX
    Explanations

    holding hands or touching

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

    The neuron strongly activates on mentions of “hand,” especially in contexts of physical contact or holding someone’s hand.

    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
    禮
    -0.74
     λά
    -0.70
     הופ
    -0.69
     sürd
    -0.69
    なりません
    -0.68
    吏
    -0.68
    PRF
    -0.67
    umbang
    -0.66
    Hutch
    -0.66
    夥
    -0.66
    POSITIVE LOGITS
     holding
    3.64
     hand
    3.09
    Holding
    3.05
    holding
    3.00
     Holding
    2.98
     hold
    2.64
     HOLD
    2.48
    HOLD
    2.36
     holds
    2.33
    Hold
    2.31
    Activations Density 0.019%

    No Known Activations