© 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. 34-GEMMASCOPE-RES-131K
    4. 23580
    Prev
    Next
    INDEX
    Explanations

    molecular structure representations

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

    scientific and technical terms related to molecular structures, particularly in chemical and biological research papers.

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

    The neuron responds to scientific or technical terminology—especially words you’d see in molecular‐biology or chemistry research write-ups.

    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
     XCTest
    -0.80
    scanner
    -0.78
    letka
    -0.78
     безо
    -0.77
     Pineapple
    -0.75
    ixel
    -0.73
    ęła
    -0.72
    isiaj
    -0.72
    结
    -0.72
    Scanning
    -0.71
    POSITIVE LOGITS
     cartoon
    1.16
     representations
    1.16
     representation
    1.16
     ribbon
    1.11
     Representations
    1.03
     rendering
    0.98
     Colour
    0.94
     ribbons
    0.93
    Representation
    0.92
     représentation
    0.91
    Activations Density 0.024%

    No Known Activations