© 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. 47945
    Prev
    Next
    INDEX
    Explanations

    study abroad admissions

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

    The neuron primarily activates on tokens written entirely in uppercase (including numeric sequences), effectively spotting all-caps words or numbers.

    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
     people
    -0.94
     even
    -0.88
     production
    -0.82
     on
    -0.82
     it
    -0.82
     only
    -0.81
    angkap
    -0.79
     by
    -0.79
    互联网档案馆
    -0.76
     using
    -0.75
    POSITIVE LOGITS
     universities
    1.37
     QS
    1.34
     IELTS
    1.25
     scholarships
    1.20
     visa
    1.18
     semester
    1.16
    student
    1.11
     Study
    1.11
     étudiants
    1.11
     study
    1.09
    Activations Density 0.020%

    No Known Activations