© 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. 13317
    Prev
    Next
    INDEX
    Explanations

    beginning of a phrase

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

    This neuron responds to the import/require of the JavaScript “symbol” polyfill (i.e. occurrences of the core-js symbol module in code).

    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
     konkurs
    -1.36
     its
    -1.35
     fotografias
    -1.30
     tunik
    -1.26
    lampe
    -1.26
    dekat
    -1.25
     karier
    -1.25
     kompati
    -1.20
     abstrak
    -1.19
     katalog
    -1.18
    POSITIVE LOGITS
    le
    1.54
    ud
    1.32
    re
    1.28
    ara
    1.28
    te
    1.20
    ha
    1.19
    na
    1.18
    us
    1.17
    ue
    1.16
    ne
    1.15
    Activations Density 0.000%

    No Known Activations