© 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. 75507
    Prev
    Next
    INDEX
    Explanations

    Brother printers

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

    The neuron strongly activates on occurrences of “used” (often in the phrase “frequently used”), flagging mentions of that word in technical descriptions.

    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
     hanging
    -1.78
     hanged
    -1.72
     hang
    -1.66
    Hanging
    -1.35
    hang
    -1.35
    hanging
    -1.33
     hangs
    -1.28
     hung
    -1.27
    HANG
    -1.24
    Hang
    -1.22
    POSITIVE LOGITS
     MFC
    0.96
    MSB
    0.93
    Brother
    0.93
     Brother
    0.92
     брат
    0.88
    Gear
    0.82
    atka
    0.81
     Nish
    0.75
     présentés
    0.75
     BROTHER
    0.74
    Activations Density 0.019%

    No Known Activations