© 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. 128815
    Prev
    Next
    INDEX
    Explanations

    sentence structure and grammar

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

    The neuron is triggered by meta‐textual markers and labels—things like “Q:”, “A:”, “In sentence B,” quotation marks, section labels, and similar structural annotations.

    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
     for
    -1.48
    朱印
    -1.38
    enseignements
    -1.38
     who
    -1.37
    taya
    -1.35
    tierte
    -1.27
     endast
    -1.26
    %");
    -1.23
     mycket
    -1.22
    =[]
    
    -1.20
    POSITIVE LOGITS
     then
    1.95
     your
    1.71
     they
    1.53
     use
    1.52
     использовании
    1.27
     specific
    1.26
     using
    1.21
     באמצעות
    1.19
     kemudian
    1.17
    }{||
    1.16
    Activations Density 0.113%

    No Known Activations