© 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. 71530
    Prev
    Next
    INDEX
    Explanations

    forms, quality, policies

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

    This neuron detects the module path strings (particularly relative imports like “from './font'”) in ES6 import statements.

    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
     to
    -1.16
    uitton
    -1.02
    /}.
    -0.96
     ideen
    -0.93
    especie
    -0.92
    啤酒
    -0.91
     FormBuilder
    -0.91
    ooled
    -0.90
     FAT
    -0.90
    扼
    -0.89
    POSITIVE LOGITS
    GetField
    1.05
     other
    1.05
    取締
    0.95
     your
    0.95
    驕
    0.94
     keeping
    0.94
    0.93
    監視
    0.93
     digunakan
    0.91
     layanan
    0.90
    Activations Density 0.002%
    No Known Activations