© 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. 118411
    Prev
    Next
    INDEX
    Explanations

    digital technology, IoT solutions, Gear, JavaOS

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

    The neuron fires on passages announcing new tech products—especially their model names, numeric specs, pricing, and availability details.

    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
     companies
    -0.81
    Aprove
    -0.80
    Siapa
    -0.77
    wig
    -0.76
     seasoned
    -0.76
     topper
    -0.76
     iPad
    -0.73
     accused
    -0.71
    rika
    -0.70
    都需要
    -0.68
    POSITIVE LOGITS
     Devices
    1.00
    Devices
    0.87
    线下
    0.86
    Device
    0.85
     Device
    0.84
    devices
    0.83
     TEC
    0.81
    INGEN
    0.81
     ENTERTAINMENT
    0.79
    otho
    0.79
    Activations Density 0.009%

    No Known Activations