© 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. 34-GEMMASCOPE-RES-131K
    7. 107193
    Prev
    Next
    INDEX
    Explanations

    Grails

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

    This neuron responds to the vertical‐bar character (“|”) used as a text delimiter or ASCII‐art element.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    |
    -1.50
     Aceite
    -1.01
    Πηγή
    -1.00
     been
    -0.99
     Concluding
    -0.95
     braços
    -0.94
    Nolan
    -0.94
    ckte
    -0.93
     İs
    -0.91
    malige
    -0.90
    POSITIVE LOGITS
     \
    1.06
    all
    1.02
    LC
    1.01
    re
    1.00
    V
    0.98
    رحلة
    0.95
     nawet
    0.95
    _));
    0.94
     dokonce
    0.94
     rifi
    0.94
    Activations Density 0.049%

    No Known Activations