© 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. 45697
    Prev
    Next
    INDEX
    Explanations

    medical evaluation

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

    phrases related to seeking or requiring medical attention or healthcare services.

    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
    trina
    -0.91
     patient
    -0.88
    cieli
    -0.85
    shutil
    -0.85
    ્
    -0.77
    iço
    -0.76
    時半
    -0.76
     medži
    -0.75
    meaux
    -0.74
    kela
    -0.74
    POSITIVE LOGITS
     evaluation
    2.84
     evaluated
    2.16
     evaluations
    2.11
     Evaluation
    2.08
     assessment
    2.08
    evaluation
    2.05
     examination
    1.95
    Evaluation
    1.95
     EVALUATION
    1.89
     eval
    1.84
    Activations Density 0.061%

    No Known Activations