© 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. 10-GEMMASCOPE-RES-131K
    7. 101893
    Prev
    Next
    INDEX
    Explanations

    relative clauses starting with which

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

    The neuron consistently activates on the prepositional phrase “to which.”

    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
    蔑
    -1.91
    ﹕
    -1.84
    雳
    -1.82
     Kür
    -1.77
     圖片
    -1.72
    嗐
    -1.66
    家が
    -1.64
     tzu
    -1.63
     將
    -1.56
    蹋
    -1.55
    POSITIVE LOGITS
     ก็
    2.17
     you
    2.02
    雱
    1.90
     ส์
    1.88
     และ
    1.82
     Lösungen
    1.81
    艽
    1.81
    ౮
    1.80
     mogą
    1.79
    蟥
    1.79
    Activations Density 0.018%

    No Known Activations