© 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. 130782
    Prev
    Next
    INDEX
    Explanations

    This neuron detects code block boundaries and control‐flow delimiters (e.g. closing “}” braces and “else”/“#else” tokens).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    bound vehicles

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    izzate
    -1.17
    $+$
    -1.01
    uitton
    -0.99
    ꞌ
    -0.99
    $*$
    -0.98
    !!!!!!!!!!!!!!!!
    -0.97
    ''',
    -0.97
    QRST
    -0.96
    *</
    -0.96
    sill
    -0.95
    POSITIVE LOGITS
     plutôt
    1.08
    ının
    1.04
     görüntüsü
    1.03
    Màu
    0.98
     normalidad
    0.95
    zło
    0.93
     malah
    0.92
    engkapnya
    0.91
    せよ
    0.91
    òs
    0.90
    Activations Density 0.003%

    No Known Activations