© 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. 81630
    Prev
    Next
    INDEX
    Explanations

    academic majors and studies

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

    The neuron detects numerical information—tokens that express counts, quantities, or years.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    mentions of higher-education contexts, especially university degrees, majors, academic programs/requirements, and student status or changes in field of study.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    text describing academic majors and educational backgrounds.

    oai_token-act-pair · claude-4-5-sonnetTriggered 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
     않습니다
    -0.76
     lọ
    -0.73
    ローマ
    -0.70
    品です
    -0.69
     vitaminas
    -0.69
    ذه
    -0.69
    纲
    -0.68
    алы
    -0.67
    CURL
    -0.66
    
    -0.66
    POSITIVE LOGITS
     majors
    4.25
     majoring
    3.86
     maj
    3.50
    maj
    3.22
    Maj
    3.11
     Maj
    2.98
     Majors
    2.97
     major
    2.83
    major
    2.78
     Major
    2.69
    Activations Density 0.078%

    No Known Activations