© 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. 23884
    Prev
    Next
    INDEX
    Explanations

    electronic hardware and modules

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

    The neuron activates on blocks of text listing detailed hardware product specifications (e.g. I/O counts, form factors, interfaces, and configuration options).

    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
    cyclopedia
    -0.99
    edding
    -0.96
     evening
    -0.95
    ꞌ
    -0.93
     знал
    -0.91
     hilfreich
    -0.91
    比賽
    -0.89
    lepiej
    -0.88
    诙
    -0.87
    因為
    -0.87
    POSITIVE LOGITS
     controller
    1.54
     modules
    1.52
     hardware
    1.45
     module
    1.42
    controller
    1.38
     firmware
    1.37
     rugged
    1.32
     ($("#
    1.30
     controllers
    1.30
     compatible
    1.29
    Activations Density 0.084%

    No Known Activations