© 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. 10-GEMMASCOPE-RES-131K
    7. 90338
    Prev
    Next
    INDEX
    Explanations

    Cove place names and related words

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

    The neuron strongly activates on occurrences of the substring “cove,” especially in place‐ or proper‐noun contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    蠵
    -2.86
     notwendigen
    -2.64
     ランチ
    -2.59
     tatsäch
    -2.58
    ly
    -2.48
    In
    -2.45
     vollständige
    -2.44
    夤
    -2.44
     erfolgreiche
    -2.38
    瑧
    -2.38
    POSITIVE LOGITS
    卝
    3.17
     But
    3.02
    臜
    2.97
     uſed
    2.89
    ໊
    2.83
    赑
    2.75
     แต่
    2.75
    岽
    2.72
     originaire
    2.69
     we
    2.67
    Activations Density 0.004%

    No Known Activations