© 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. 107604
    Prev
    Next
    INDEX
    Explanations

    traumatic brain injury

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

    medical terms related to traumatic injuries, particularly focusing on traumatic brain injury (TBI).

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

    The neuron selectively activates on words and phrases related to trauma and traumatic stress (e.g., “traumatic,” “trauma,” “PTSD”).

    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
    7
    -1.11
    5
    -1.02
     =
    -0.99
    p
    -0.96
    </i>
    -0.95
    g
    -0.93
    '
    -0.91
    DS
    -0.90
    ().
    -0.88
    ("
    -0.88
    POSITIVE LOGITS
     trauma
    1.73
     Trauma
    1.60
     traum
    1.54
     Traum
    1.38
    Trauma
    1.26
    trauma
    1.23
     reservas
    1.09
     traumatic
    1.04
     vécu
    1.04
     experiences
    1.00
    Activations Density 0.013%

    No Known Activations