© 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. 104047
    Prev
    Next
    INDEX
    Explanations

    diploma and diplomate

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

    The neuron activates on mentions of academic credentials—especially the word “diploma” (and its variants).

    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
    閦
    -3.09
    隄
    -3.00
     continually
    -2.94
    铪
    -2.91
    說
    -2.77
    茑
    -2.70
    งิน
    -2.70
     stubbornly
    -2.64
    欉
    -2.64
    梣
    -2.55
    POSITIVE LOGITS
    CurtirCurtir
    2.83
    羕
    2.48
    .
    2.42
    羣
    2.42
    やった
    2.34
    姈
    2.34
     kaca
    2.31
    がんば
    2.28
     praktis
    2.28
    :";
    2.25
    Activations Density 0.002%

    No Known Activations