© 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. 10-GEMMASCOPE-RES-131K
    7. 65188
    Prev
    Next
    INDEX
    Explanations

    Search, Q, OB

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

    The neuron fires on path literals in require/import statements that include “webpack” (especially webpack plugin package names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    '
    -3.02
    u
    -2.19
    ちなみに
    -2.17
     andere
    -1.98
     ‘
    -1.91
    e
    -1.84
    1
    -1.79
    ‘
    -1.77
    re
    -1.69
     don
    -1.67
    POSITIVE LOGITS
     мы
    2.13
    ELING
    2.02
     dritten
    2.02
    歺
    1.98
    齜
    1.91
    一丝
    1.90
    ativní
    1.87
    ꠥ
    1.83
    𖡼
    1.81
    пыта
    1.78
    Activations Density 0.003%

    No Known Activations