© 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. 10-GEMMASCOPE-RES-131K
    4. 130317
    Prev
    Next
    INDEX
    Explanations

    ailments and disorders

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

    medical conditions and symptoms, particularly those affecting the head, brain, or sensory systems.

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

    This neuron detects multiword compound names of conditions or disorders (e.g. jet lag, shin splints, tunnel vision, seasonal affective disorder).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     by
    -1.94
     to
    -1.85
     ‘
    -1.63
     various
    -1.54
     at
    -1.48
     demonstrates
    -1.40
     diverse
    -1.40
     даже
    -1.39
     There
    -1.35
     in
    -1.34
    POSITIVE LOGITS
    狨
    1.53
    ⍽
    1.48
     komplet
    1.48
    夲
    1.47
    必须要
    1.45
     nieuwe
    1.43
    堔
    1.41
    rification
    1.41
    aneity
    1.41
     catég
    1.39
    Activations Density 0.097%

    No Known Activations