© 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. 7046
    Prev
    Next
    INDEX
    Explanations

    daily life activities and their frequency

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

    The neuron fires on vocabulary referring to ordinary human routines and circumstances—especially mentions of people’s work, daily life, and related activities.

    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
    beforeAll
    -0.80
    (&:
    -0.76
    Proces
    -0.75
    raten
    -0.75
    ätzen
    -0.75
    霁
    -0.75
     Cress
    -0.74
    imetsu
    -0.74
    pade
    -0.74
    üchte
    -0.74
    POSITIVE LOGITS
     work
    1.14
     daily
    1.06
     seldom
    0.94
     coppia
    0.85
     rarely
    0.85
     occasionally
    0.84
    преки
    0.83
     commute
    0.82
     often
    0.81
     usually
    0.81
    Activations Density 0.010%

    No Known Activations