© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38306
    Prev
    Next
    INDEX
    Explanations

    risk prediction and stratification

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

    patterns in text related to risk prediction, patient outcomes, and medical/clinical assessment tools.

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

    The neuron strongly activates on numeric tokens and technical clinical-study vocabulary—i.e. numbers and formal research terms in medical/scientific abstracts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     ویتامین
    -1.02
    STEVE
    -1.00
     sull
    -0.99
    KIM
    -0.97
     legales
    -0.96
    ׇ
    -0.94
     Rogan
    -0.94
     djur
    -0.93
    veless
    -0.93
     öpp
    -0.92
    POSITIVE LOGITS
     prediction
    1.79
     predictive
    1.78
     risk
    1.71
     predicting
    1.66
     predictions
    1.63
     predict
    1.55
     based
    1.48
     predicted
    1.48
     predicts
    1.45
     Predict
    1.36
    Activations Density 0.245%

    No Known Activations