© 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. 95835
    Prev
    Next
    INDEX
    Explanations

    beginning of phrases or sections

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

    The neuron detects occurrences of the configuration property “source” (as in the jQuery autocomplete option) in code blocks.

    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
    commodation
    -1.47
     ibland
    -1.37
     femininos
    -1.34
    籥
    -1.34
     手
    -1.30
    ⚋
    -1.27
     your
    -1.24
    complished
    -1.23
    e
    -1.23
    everything
    -1.23
    POSITIVE LOGITS
     –
    1.30
    瀦
    1.24
     طریق
    1.23
     pemuda
    1.21
    ’
    1.16
    Bibliote
    1.13
    我和
    1.10
     besieged
    1.09
    ↵
    1.06
     deterred
    1.05
    Activations Density 0.000%

    No Known Activations