© 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. 50030
    Prev
    Next
    INDEX
    Explanations

    NOAA data and services

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

    The neuron activates on mentions of proper names for government or institutional organizations (e.g. acronyms like NOAA or full agency titles).

    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
    conjug
    -0.72
    gio
    -0.71
     stuffy
    -0.69
     點
    -0.68
     vapor
    -0.66
    ртка
    -0.66
    cydow
    -0.65
     lasagna
    -0.65
    >(),
    -0.65
     兩
    -0.65
    POSITIVE LOGITS
     NOAA
    1.74
    NOAA
    1.45
    noaa
    1.17
     Национа
    1.02
     Commerce
    0.96
     National
    0.94
     weather
    0.93
    ності
    0.88
    NOS
    0.85
    Boulder
    0.85
    Activations Density 0.030%

    No Known Activations