© 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. 6925
    Prev
    Next
    INDEX
    Explanations

    patients and medical contexts

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

    copyright and licensing statements in software code.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on punctuation tokens, especially periods (“.”) and semicolons (“;”) in code.

    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
     psychologist
    -0.88
     psychologists
    -0.85
    外部リンク
    -0.81
     Pader
    -0.79
    windig
    -0.79
    鋲
    -0.79
     melan
    -0.78
     campan
    -0.77
     CATALOG
    -0.77
     ecclesias
    -0.77
    POSITIVE LOGITS
     patient
    2.17
     patients
    2.11
    patient
    1.88
    Patient
    1.86
     Patients
    1.82
     Patient
    1.81
    Patients
    1.64
    patients
    1.51
     pacientes
    1.46
    患者
    1.41
    Activations Density 0.014%

    No Known Activations