© 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. 72427
    Prev
    Next
    INDEX
    Explanations

    proton in science and medicine

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

    The neuron detects scientific terms related to protons, especially in chemistry and biochemistry contexts.

    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_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
    ﻚ
    -2.67
    ﮑ
    -2.63
     Warga
    -2.34
    ⸫
    -2.33
    𝐊
    -2.25
    笮
    -2.25
    gées
    -2.23
    镦
    -2.23
     kuiten
    -2.23
    ใหม่
    -2.23
    POSITIVE LOGITS
    n
    3.44
    ization
    3.08
    le
    2.77
    er
    2.73
    {
    2.69
    en
    2.61
     mencion
    2.56
    翃
    2.53
    an
    2.52
    न
    2.50
    Activations Density 0.004%

    No Known Activations