© 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. 34-GEMMASCOPE-RES-131K
    7. 118271
    Prev
    Next
    INDEX
    Explanations

    buffer solutions and detergents

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

    chemical buffer solutions and laboratory reagents in scientific texts.

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

    The neuron flags technical measurement tokens—numbers, units, buffer and reagent names (e.g. PBS, Triton X-100, concentrations)—in scientific methods descriptions.

    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
    囪
    -0.78
     evac
    -0.76
     attracted
    -0.76
    isDebugEnabled
    -0.73
    Parameteri
    -0.72
    Redaktion
    -0.71
     srs
    -0.71
    Naturally
    -0.71
    誥
    -0.71
    WATER
    -0.71
    POSITIVE LOGITS
     Tween
    1.03
     PBS
    1.00
     Washing
    0.94
     washing
    0.85
    Tween
    0.85
     tween
    0.77
    tween
    0.77
     Laundry
    0.76
    PBS
    0.76
     detergent
    0.76
    Activations Density 0.015%

    No Known Activations