© 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. 50153
    Prev
    Next
    INDEX
    Explanations

    home activities and relaxation

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

    The neuron detects expressions of cozy, at-home leisure or relaxation actions (e.g. “curl up with a book,” “sit back with the family,” “laze around,” “settle down,” “sip a warm cup of tea”).

    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
    プローチ
    -0.85
     weddings
    -0.82
    LastModified
    -0.80
     locker
    -0.78
    EventManager
    -0.77
     visit
    -0.77
    haran
    -0.76
     stand
    -0.76
     vstup
    -0.76
    quesa
    -0.75
    POSITIVE LOGITS
     Netflix
    2.11
    Netflix
    1.93
     netflix
    1.83
    netflix
    1.64
     binge
    1.63
     movies
    1.52
     movie
    1.41
    Movie
    1.31
     couch
    1.28
     cozy
    1.26
    Activations Density 0.030%

    No Known Activations