© 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. 111127
    Prev
    Next
    INDEX
    Explanations

    academic master's degrees

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

    The neuron fires on tokens naming graduate‐level academic degrees (especially master’s degrees and related degree terms).

    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
     Substanz
    -0.98
     shotguns
    -0.85
     Shotgun
    -0.81
    discount
    -0.79
     Baptists
    -0.77
    イオン
    -0.77
     DISCIP
    -0.77
     blouse
    -0.77
     Factories
    -0.77
     усилия
    -0.75
    POSITIVE LOGITS
     of
    2.11
     in
    1.34
     degree
    1.11
     méret
    0.95
    atchewan
    0.94
     öğretmen
    0.92
     science
    0.90
    邝
    0.87
     günü
    0.84
     telur
    0.83
    Activations Density 0.010%

    No Known Activations