© 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. 22-GEMMASCOPE-RES-131K
    7. 15828
    Prev
    Next
    INDEX
    Explanations

    list labels

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

    This neuron responds to structural syntax markers—braces in JSON or code and XML/HTML tag delimiters.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ẵng
    -1.08
    Odpo
    -1.07
     odkazy
    -1.07
     rokov
    -1.00
    besos
    -0.98
    kanak
    -0.98
     dziecko
    -0.96
    ırs
    -0.95
    €“
    -0.94
    ᵉ
    -0.94
    POSITIVE LOGITS
     einzige
    1.00
     ardent
    0.94
     aident
    0.94
     einzigen
    0.88
     Fähig
    0.88
     unregister
    0.88
    c
    0.86
     inplace
    0.85
    Nro
    0.85
    q
    0.83
    Activations Density 0.004%

    No Known Activations