© 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. 34-GEMMASCOPE-RES-131K
    4. 118057
    Prev
    Next
    INDEX
    Explanations

    close-up and close range

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

    The neuron strongly activates on words and compounds that denote proximity or nearness—e.g. “close-up,” “up close,” “closer,” and “close range.”

    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
     close
    -0.93
     closest
    -0.81
     oluşan
    -0.79
    leuth
    -0.78
    寸
    -0.77
    larımız
    -0.76
     Erkenntnis
    -0.73
    larla
    -0.73
     climbed
    -0.72
    hướng
    -0.72
    POSITIVE LOGITS
     up
    0.98
     view
    0.96
     views
    0.95
     perspective
    0.93
     detail
    0.92
     kanton
    0.89
     encounter
    0.86
     Detail
    0.86
     encounters
    0.85
    detail
    0.84
    Activations Density 0.014%

    No Known Activations