© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45539
    Prev
    Next
    INDEX
    Explanations

    GUIDs and ObjectIDs

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

    The neuron fires on tokens that are parts of unique identifier literals—e.g. GUID/UUID or ObjectId values or constructors.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    ."
    -1.79
    ers
    -1.69
    脔
    -1.67
     beneficios
    -1.66
     esencial
    -1.54
    骸
    -1.54
    栒
    -1.52
    fm
    -1.52
     embodiment
    -1.50
     assurer
    -1.48
    POSITIVE LOGITS
     of
    2.02
     Vereinigten
    1.43
     demselben
    1.36
     Idk
    1.35
     weißem
    1.34
    ’
    1.33
     jūs
    1.33
    6
    1.32
    的事情
    1.30
    bringung
    1.29
    Activations Density 0.008%

    No Known Activations