© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9183
    Prev
    Next
    INDEX
    Explanations

    `.then(response

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

    The neuron strongly activates on the “=>” token used in code (e.g. arrow functions or lambda expressions).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    𝓻
    1.13
    𝟏
    1.09
    𝔯
    1.03
    ﻦ
    1.00
    이라고
    0.99
    ның
    0.98
    Ди
    0.96
    pok
    0.96
     compactly
    0.95
     alternately
    0.94
    POSITIVE LOGITS
    ą
    1.23
    ü
    1.04
    க
    1.00
    í
    0.99
    يد
    0.92
    ak
    0.91
    ಿಕ
    0.89
     froide
    0.88
     وہ
    0.88
    Quelle
    0.87
    Activations Density 0.000%

    No Known Activations