© 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. 630
    Prev
    Next
    INDEX
    Explanations

    academic honors and awards

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

    The main thing this neuron does is detect mentions of academic qualifications and honors (degrees, honors distinctions, dean’s-list placements, graduation years, etc.).

    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
     размеры
    -0.81
    corpion
    -0.77
     Crocodile
    -0.77
     gặp
    -0.75
    שלום
    -0.70
     puffer
    -0.69
     proposes
    -0.69
    上限
    -0.68
     Ense
    -0.68
    setOptions
    -0.68
    POSITIVE LOGITS
     honor
    2.03
     Dean
    1.96
     Honor
    1.95
     dean
    1.89
     honour
    1.77
    Honor
    1.77
    honor
    1.65
    Dean
    1.58
     Honour
    1.44
     honors
    1.30
    Activations Density 0.018%

    No Known Activations