© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 93015
    Prev
    Next
    INDEX
    Explanations

    use strict

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

    This neuron activates specifically on JavaScript’s "use strict" directive.

    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
     of
    -1.71
    そして
    -1.38
    ですが
    -1.34
    また
    -1.26
    ť
    -1.23
    しかし
    -1.20
    癖
    -1.20
     ранее
    -1.20
    だけど
    -1.18
     而
    -1.16
    POSITIVE LOGITS
    為に
    1.23
    の方法
    1.23
    اشتم
    1.20
    Beberapa
    1.18
    ッキリ
    1.17
     blijkt
    1.17
    歩く
    1.16
    んですよ
    1.14
    ことも
    1.13
    たちに
    1.13
    Activations Density 0.002%

    No Known Activations