© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 73864
    Prev
    Next
    INDEX
    Explanations

    double staining

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

    technical or scientific terms involving pairs or duplicates, like "double clutch," "double contrast," or "double staining."

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

    This neuron detects occurrences of the word “double” (including its use in compound phrases like “double immunostaining,” “double‐contrast,” etc.).

    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
     tuvo
    -1.55
     is
    -1.52
    </u>
    -1.48
    出了一
    -1.45
    察觉
    -1.45
    嵛
    -1.41
    gnancy
    -1.39
     suele
    -1.36
     bekannten
    -1.34
    PCL
    -1.32
    POSITIVE LOGITS
    double
    1.77
    When
    1.69
    They
    1.63
    With
    1.47
    After
    1.41
     double
    1.41
     двой
    1.41
    2
    1.32
    双
    1.30
    6
    1.27
    Activations Density 0.065%

    No Known Activations