© 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. 36428
    Prev
    Next
    INDEX
    Explanations

    UI class definitions

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

    The neuron is specifically detecting the left square‐bracket character “[.”

    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
     kontin
    -1.13
     konkurs
    -1.04
     身
    -1.00
     their
    -0.99
     they
    -0.98
    ename
    -0.98
    lierung
    -0.97
    tisch
    -0.95
     jaja
    -0.94
    侑
    -0.93
    POSITIVE LOGITS
     крайней
    1.20
     trám
    1.18
     ず
    1.13
     фильмы
    1.13
     erworben
    1.12
     който
    1.11
     tropicales
    1.11
     oreille
    1.09
     lutar
    1.07
     мужская
    1.07
    Activations Density 0.000%

    No Known Activations