© 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. 60591
    Prev
    Next
    INDEX
    Explanations

    eligible groups for care

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

    The neuron fires on tokens typical of clinical‐research reporting—especially numeric data (e.g. years, counts, dosages) and medical terminology around chronic conditions, vaccination, and study recommendations.

    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
     ultrasonic
    -0.75
     barnet
    -0.74
     Alkali
    -0.73
    コスパ
    -0.70
     bibli
    -0.69
     bolas
    -0.69
    mint
    -0.68
     INSTAGRAM
    -0.68
     Ultrasonic
    -0.68
     encontré
    -0.66
    POSITIVE LOGITS
     vulnerable
    1.64
     eligible
    1.48
     risk
    1.32
     priority
    1.30
     Vulnerable
    1.27
     Eligible
    1.19
    eligible
    1.16
     vulné
    1.14
    Eligible
    1.13
    priority
    1.13
    Activations Density 0.008%

    No Known Activations