© 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. 34-GEMMASCOPE-RES-131K
    7. 92325
    Prev
    Next
    INDEX
    Explanations

    bra followed by specific suffixes

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

    The neuron responds to occurrences of the letter sequence “Bra” at the start of words or 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_34/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
     formal
    -0.77
     comparative
    -0.76
     لكرة
    -0.75
    álás
    -0.69
    قدام
    -0.69
    handlungen
    -0.69
    ссор
    -0.69
     economico
    -0.68
    记住
    -0.68
     more
    -0.68
    POSITIVE LOGITS
    Bra
    1.31
     Bra
    1.17
    bra
    1.17
     bra
    1.16
     BRA
    1.03
     brag
    0.97
    ブラ
    0.91
     Braga
    0.85
    ſte
    0.79
     ブラ
    0.79
    Activations Density 0.031%

    No Known Activations