© 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. 103960
    Prev
    Next
    INDEX
    Explanations

    degree types and requirements

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

    The main thing this neuron does is detect mentions of academic qualifications—terms like “degree,” “diploma,” “certificate,” and specific degree names.

    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
     デニム
    -0.86
    aggiare
    -0.83
    heiros
    -0.83
     zvíř
    -0.82
    اری
    -0.82
    PDIR
    -0.80
    チャンネル
    -0.80
     deterior
    -0.79
    ordeel
    -0.79
    刧
    -0.78
    POSITIVE LOGITS
     awarded
    1.49
     holder
    1.41
     conferred
    1.41
     holders
    1.27
     recipients
    1.21
     earned
    1.20
    earned
    1.10
     awarding
    1.06
     Holder
    1.05
     recipient
    1.03
    Activations Density 0.018%

    No Known Activations