© 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. 10-GEMMASCOPE-RES-131K
    4. 48236
    Prev
    Next
    INDEX
    Explanations

    common interjections and phrases

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

    The neuron is detecting proper names (capitalized personal names) in running text.

    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
    </h3>
    -3.17
    ୌ
    -2.97
    媗
    -2.89
    na
    -2.77
    玙
    -2.70
    𓄹
    -2.56
    m
    -2.56
    嫆
    -2.55
    that
    -2.53
     letz
    -2.52
    POSITIVE LOGITS
    </b>
    2.50
    一個
    2.47
     consegui
    2.39
     struck
    2.33
     defied
    2.16
    美丽的
    2.14
     admon
    2.11
     quién
    2.08
     своей
    2.05
    很赞
    2.05
    Activations Density 0.003%

    No Known Activations