© 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. 93959
    Prev
    Next
    INDEX
    Explanations

    academic honors and distinction

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

    The neuron strongly activates on terms and numbers associated with academic credentials—mentions of graduating, degrees, honors, prizes, and related classifications.

    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
    rook
    -0.78
    ]';
    -0.73
    iar
    -0.71
    げ
    -0.69
     фами
    -0.68
    ítica
    -0.67
    処理
    -0.67
    Barra
    -0.66
    airro
    -0.66
    تين
    -0.66
    POSITIVE LOGITS
     flying
    2.22
     distinction
    1.98
    flying
    1.77
     Distinction
    1.72
     honors
    1.52
    Flying
    1.48
     honours
    1.34
    Dist
    1.31
     Flying
    1.30
     distinción
    1.20
    Activations Density 0.027%

    No Known Activations