© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67131
    Prev
    Next
    INDEX
    Explanations

    chromatography and mass spectrometry

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

    analytical chemistry terms related to liquid chromatography techniques.

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

    The neuron activates on mentions of analytical chemistry methods, especially liquid chromatography (and related LC-MS) techniques.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    y
    -1.08
     Nearby
    -1.01
     and
    -1.00
    {
    -0.99
    の人に
    -0.98
    nearby
    -0.97
     وزار
    -0.97
     eorum
    -0.97
     &
    -0.95
     communication
    -0.95
    POSITIVE LOGITS
    Toeschouwers
    1.30
    ˾
    1.28
    compañ
    1.24
    ספר
    1.23
    ėte
    1.22
     slalom
    1.21
    HPLC
    1.21
    */),
    1.19
     Solskjaer
    1.19
    DebuggerStep
    1.17
    Activations Density 0.045%

    No Known Activations