© 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. 30397
    Prev
    Next
    INDEX
    Explanations

    academic achievement scholarships

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

    The neuron detects mentions of academic achievements and honors (e.g. graduation status, test scores, scholarships, percentages, and awards).

    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
    諱
    -0.79
     штра
    -0.73
    蛾
    -0.72
    trero
    -0.69
    GraphicsUnit
    -0.68
    año
    -0.67
    enderung
    -0.66
    Location
    -0.66
    항
    -0.66
     формате
    -0.65
    POSITIVE LOGITS
     scholarship
    1.23
     semifinal
    1.20
     scholar
    1.16
     Merit
    1.09
     merit
    1.07
     scholars
    1.05
     Scholars
    1.05
     recognition
    1.00
     presidential
    0.98
     Scholar
    0.95
    Activations Density 0.013%

    No Known Activations