© 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. 60284
    Prev
    Next
    INDEX
    Explanations

    patient data, FHIR, programming code

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

    The neuron strongly activates on code identifiers or type/class names (PascalCase tokens) in programming contexts.

    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
     λειτουργ
    -0.84
     tegens
    -0.81
     Pounds
    -0.78
    ээ
    -0.78
     Remedies
    -0.77
     both
    -0.75
     sterren
    -0.74
     Pote
    -0.74
     Advocates
    -0.73
     Disciples
    -0.73
    POSITIVE LOGITS
     patient
    1.11
     copiar
    1.01
     Patient
    0.98
    fhir
    0.96
    patient
    0.96
    digm
    0.93
     FH
    0.93
     patients
    0.91
     pacientes
    0.90
    CAPÍTULO
    0.90
    Activations Density 0.002%

    No Known Activations