© 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. 98418
    Prev
    Next
    INDEX
    Explanations

    code delimiters

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

    This neuron detects code tokens that are method calls (identifiers followed by “()” and a semicolon).

    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
     their
    -1.13
     pesquisas
    -1.01
    :
    -0.96
    がありますが
    -0.94
     realizarse
    -0.93
    特に
    -0.92
    という感じ
    -0.91
    nové
    -0.90
    着一个
    -0.90
     οι
    -0.88
    POSITIVE LOGITS
     such
    1.18
     pavimento
    1.05
     таких
    1.02
     testamento
    0.98
    ಿ
    0.95
    もう少し
    0.94
    (^_^
    0.93
     rosse
    0.93
    ：“……”
    0.91
     bessere
    0.91
    Activations Density 0.008%

    No Known Activations