© 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. 8162
    Prev
    Next
    INDEX
    Explanations

    Zach and Zack names

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

    The neuron detects occurrences of the name “Zach” (including variants like Zachary, Zachariah, 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
    鹮
    -2.61
    鹋
    -2.56
     Ꮎ
    -2.47
     彈
    -2.45
     estudi
    -2.41
    jaqueta
    -2.38
     兒童
    -2.36
    出了一
    -2.36
    ⽽
    -2.36
     dañ
    -2.33
    POSITIVE LOGITS
    the
    3.39
    7
    2.78
    4
    2.77
    as
    2.63
    0
    2.61
    s
    2.50
    l
    2.41
     worin
    2.36
    2
    2.36
     antichi
    2.34
    Activations Density 0.008%

    No Known Activations