© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109784
    Prev
    Next
    INDEX
    Explanations

    Theoretical physics and biology

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

    The neuron activates for academic affiliations, particularly those containing the word "Theoretical" followed by a field like "Physics" in scientific papers or institutional addresses.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    urgical
    -0.97
    énieur
    -0.89
     вашем
    -0.84
    например
    -0.83
    ñadir
    -0.80
     zweiter
    -0.79
     голубой
    -0.79
     última
    -0.78
    坨
    -0.76
    mines
    -0.75
    POSITIVE LOGITS
     biology
    1.35
     physics
    1.30
     psychiatry
    1.25
     genetics
    1.22
     psychology
    1.22
     neuroscience
    1.16
     geology
    1.07
     phys
    1.05
     astronomy
    1.04
     medicine
    1.01
    Activations Density 0.179%

    No Known Activations