© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 70494
    Prev
    Next
    INDEX
    Explanations

    ending code blocks with `]`

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

    The neuron fires strongly on long bracketed sequences (array or list literals with many elements).

    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
     scholarly
    -2.38
    ᠌
    -2.14
     Budaya
    -2.13
    extAlignment
    -2.09
    🧌
    -2.06
    乚
    -1.98
    A
    -1.96
    崀
    -1.92
     strana
    -1.88
    ztes
    -1.88
    POSITIVE LOGITS
    at
    2.67
    垍
    2.58
    筇
    2.30
     Можно
    2.20
    ]
    2.13
     remporté
    1.99
    j
    1.98
    к
    1.93
    é
    1.92
    嵛
    1.92
    Activations Density 0.041%

    No Known Activations