© 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. 75433
    Prev
    Next
    INDEX
    Explanations

    treating diseases and conditions

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

    medical conditions and their treatments in clinical or academic texts.

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

    The neuron is looking for contexts describing medical treatment or clinical intervention (e.g. “for treating…,” “on… after…,” “due to injury,” etc.).

    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
     cogni
    -0.77
     VizieR
    -0.76
    .»
    -0.75
     Khu
    -0.75
     STRATEGY
    -0.73
     Uli
    -0.73
     :"
    -0.73
    ebay
    -0.72
     grp
    -0.72
    ープル
    -0.72
    POSITIVE LOGITS
     condition
    1.05
     sequ
    0.98
     healed
    0.93
     diagnosed
    0.90
     disease
    0.90
     cured
    0.88
     conservative
    0.88
     lying
    0.85
     minor
    0.85
     prognosis
    0.85
    Activations Density 0.005%

    No Known Activations