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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 10943
    Prev
    Next
    INDEX
    Explanations

    biological molecules and processes

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

    scientific/medical terms related to biological structures, cells, and biochemical components of the body.

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

    The neuron detects technical biomedical terms describing molecular substrates and cellular processes (e.g. oxygen, glucose, protein synthesis, intracellular energy stores, cell membrane, NMDA receptor).

    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
     with
    -2.89
     both
    -2.23
     as
    -2.22
     at
    -2.03
     before
    -2.02
     without
    -1.95
     would
    -1.91
     any
    -1.85
     using
    -1.80
     seven
    -1.75
    POSITIVE LOGITS
     که
    1.71
    commonly
    1.67
     toalla
    1.66
     pierwszej
    1.62
    給你
    1.61
     mascarilla
    1.60
     diriger
    1.59
    generally
    1.55
     interesses
    1.54
    鵙
    1.54
    Activations Density 0.355%

    No Known Activations