© 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. 8156
    Prev
    Next
    INDEX
    Explanations

    FIGHT or FLIGHT response

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

    words related to the fight or flight response.

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

    The neuron strongly activates on “fight,” “flight,” and closely related terms describing the fight-or-flight stress response.

    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
     Spherical
    -0.74
     spherical
    -0.73
    挛
    -0.70
     oscillator
    -0.69
     physics
    -0.69
    ѳ
    -0.68
     DATA
    -0.68
     retra
    -0.67
    xFFFF
    -0.67
    illary
    -0.66
    POSITIVE LOGITS
     response
    1.80
    response
    1.59
     responses
    1.50
     Response
    1.32
    RESPONSE
    1.29
     flight
    1.25
     fight
    1.24
    Response
    1.23
     Responses
    1.23
    Responses
    1.14
    Activations Density 0.037%

    No Known Activations