© 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. 6940
    Prev
    Next
    INDEX
    Explanations

    packets and samples

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

    The neuron responds strongly to mentions of packaged product units—especially “packages” and related packaging quantity phrases.

    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
     Gap
    -0.78
    Gap
    -0.76
     Sandwich
    -0.70
     Appellate
    -0.70
    JTextField
    -0.70
    Television
    -0.69
    bner
    -0.69
     basement
    -0.68
    Rgb
    -0.68
    basket
    -0.68
    POSITIVE LOGITS
     packets
    1.95
     sachets
    1.63
     mini
    1.58
     packet
    1.54
     sachet
    1.49
     miniature
    1.43
    packets
    1.43
    mini
    1.39
    Mini
    1.34
    packet
    1.33
    Activations Density 0.018%

    No Known Activations