© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27286
    Prev
    Next
    INDEX
    Explanations

    place names and subsequent terms

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

    The neuron activates on substrings of geographic proper names (place names or electoral/administrative district names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ＊＊＊
    -1.46
    来週
    -1.40
    明日は
    -1.38
    ほら
    -1.38
    為に
    -1.32
    あー
    -1.30
    不僅
    -1.29
    まさかの
    -1.28
    凄く
    -1.28
    えっ
    -1.28
    POSITIVE LOGITS
    があり
    1.71
    <bos>
    1.58
    があります
    1.50
    UCIÓN
    1.45
    があって
    1.31
    もあります
    1.30
    かで
    1.28
    which
    1.25
    なので
    1.24
    を見
    1.22
    Activations Density 0.071%

    No Known Activations