© 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. 34-GEMMASCOPE-RES-131K
    7. 57211
    Prev
    Next
    INDEX
    Explanations

    academic degrees and levels

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

    The neuron fires strongly on terms naming or referring to postgraduate degree programs (e.g. master’s, MA, PhD, postgraduate).

    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
     kiểu
    -0.85
    앰
    -0.83
     Postgraduate
    -0.82
     gewähr
    -0.82
     undergrad
    -0.81
     both
    -0.81
     hielt
    -0.80
     risulta
    -0.79
    BOTH
    -0.75
     móc
    -0.75
    POSITIVE LOGITS
     level
    1.84
     degree
    1.67
    level
    1.39
     program
    1.22
    degree
    1.17
     students
    1.16
     degrees
    1.05
     Degree
    1.05
     course
    1.03
     programs
    1.03
    Activations Density 0.034%

    No Known Activations