© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 9654
    Prev
    Next
    INDEX
    Explanations

    people and their conditions

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

    The neuron activates for references to patients in medical or clinical contexts.

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

    The neuron activates on mentions of the study population—especially the token “patients” (and similar references to people under study).

    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
     and
    -1.77
     each
    -1.53
     different
    -1.49
    。
    -1.46
     would
    -1.44
     will
    -1.41
     then
    -1.34
     it
    -1.33
     a
    -1.30
    oczes
    -1.27
    POSITIVE LOGITS
     who
    3.73
     whose
    2.25
     που
    2.23
    whose
    1.98
     of
    1.97
    who
    1.92
     that
    1.67
    ที่มี
    1.67
     tył
    1.66
    ที่
    1.66
    Activations Density 0.105%

    No Known Activations