© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100395
    Prev
    Next
    INDEX
    Explanations

    luminescence and lignin

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

    scientific terms related to luminescence and light emission in chemistry and materials science.

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

    The neuron strongly activates on specialized scientific substance names or technical terms (e.g., chemical compounds, polymers, luminescence-related words).

    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
    時間
    -2.70
    Szia
    -2.64
    他
    -2.52
    新しい
    -2.41
    -2.31
    需要
    -2.30
    Ahol
    -2.28
    她
    -2.28
    Ꮚ
    -2.27
    Üdv
    -2.25
    POSITIVE LOGITS
     of
    2.50
    *
    2.31
    ).
    2.20
    ?
    2.14
    inescence
    2.05
    [
    2.05
    2.02
     caters
    2.00
    ),
    1.99
     signifies
    1.94
    Activations Density 0.005%
    No Known Activations