© 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. 34-GEMMASCOPE-RES-131K
    7. 49977
    Prev
    Next
    INDEX
    Explanations

    academic requirements

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

    The neuron strongly activates on section headings and key terms in academic catalog pages—especially the “Degree Requirements” or similar program‐requirements headings in university course listings.

    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
    Dissertation
    -0.81
    multline
    -0.80
    🇫
    -0.79
    DZ
    -0.79
    脚本
    -0.79
    redientes
    -0.78
    ଵ
    -0.78
    latt
    -0.78
    RTSN
    -0.78
    培训
    -0.77
    POSITIVE LOGITS
     requirements
    1.69
    requirements
    1.23
     Requirements
    1.23
    Requirements
    1.09
     required
    1.05
     requirement
    1.03
     advising
    1.00
     advisors
    0.98
     advisor
    0.93
    www
    0.92
    Activations Density 0.030%

    No Known Activations