© 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. 84655
    Prev
    Next
    INDEX
    Explanations

    domain abbreviations

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

    The neuron is detecting U.S. state abbreviations used as parts of government‐style domain names (e.g. “state.fl.us,” “state.ma.us”).

    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
     celui
    -0.83
    ⼀
    -0.82
    arot
    -0.79
    իս
    -0.77
    quisites
    -0.77
    тъ
    -0.75
    sierten
    -0.75
    Philli
    -0.74
     migh
    -0.73
    теристика
    -0.73
    POSITIVE LOGITS
    밌
    0.94
    ∨
    0.77
     INTERNET
    0.77
    internet
    0.76
     BMX
    0.76
    行政区划
    0.76
    teacher
    0.75
    ---|
    0.75
    mylist
    0.75
    Alamat
    0.74
    Activations Density 0.015%

    No Known Activations