© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117144
    Prev
    Next
    INDEX
    Explanations

    hospital locations

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

    The neuron detects hospital or medical center names and their locations, particularly recognizing the pattern of a hospital name followed by a city or region in parentheses or commas.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     Veterin
    -0.84
     saiba
    -0.82
    輯
    -0.80
     veterin
    -0.78
    мати
    -0.75
    انات
    -0.74
    発
    -0.74
     Jewellery
    -0.72
    võ
    -0.71
     Veterinary
    -0.71
    POSITIVE LOGITS
     patient
    1.55
     patients
    1.51
    patient
    1.45
     Patients
    1.35
    Patients
    1.26
    Patient
    1.25
     Patient
    1.21
    patients
    1.21
     pacientes
    1.16
     hospital
    1.12
    Activations Density 0.052%

    No Known Activations