© 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. 34-GEMMASCOPE-RES-131K
    4. 102668
    Prev
    Next
    INDEX
    Explanations

    professional manufacturing

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

    The neuron activates on formatted Q&A or numbered list markers—i.e. list indices and question/answer labels like “1.”, “Q:”, “A:”, and other colons.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    madeus
    -0.80
     antidesliz
    -0.77
     mercancías
    -0.77
    recip
    -0.76
     either
    -0.75
     Chemist
    -0.74
    revista
    -0.73
    cM
    -0.72
    ствен
    -0.72
    崩
    -0.71
    POSITIVE LOGITS
     professional
    1.25
     professionnel
    1.14
     professionnelle
    1.13
     profissional
    1.05
     профессиона
    1.05
     profesional
    0.95
     professionnels
    0.94
     manufacturer
    0.94
     professionalism
    0.94
     profesionales
    0.93
    Activations Density 0.024%

    No Known Activations