© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107869
    Prev
    Next
    INDEX
    Explanations

    world's first or most

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

    The neuron strongly activates on geographic proper nouns (e.g. country names and the word “world”).

    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
    である
    -0.88
     sometimes
    -0.81
     ’
    -0.81
    我没有
    -0.80
     なし
    -0.80
    ような
    -0.80
     которые
    -0.80
     stepped
    -0.78
     являются
    -0.77
     peoples
    -0.77
    POSITIVE LOGITS
    ’
    1.05
     najbolj
    1.02
    ВЕ
    1.01
     najbardziej
    0.95
     énergé
    0.93
     suuri
    0.92
    gangenen
    0.90
    ኦ
    0.90
     layui
    0.90
     største
    0.89
    Activations Density 0.032%

    No Known Activations