© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 19968
    Prev
    Next
    INDEX
    Explanations

    DR abbreviations or acronyms

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

    The neuron strongly activates on the uppercase bigram “DR” when it appears as part of technical acronyms or identifiers.

    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
    </strong>
    -3.42
    </em>
    -3.00
    '
    -2.69
     they
    -2.63
    呖
    -2.59
    ſu
    -2.55
    秶
    -2.53
    </h3>
    -2.45
    "
    -2.33
    
    -2.33
    POSITIVE LOGITS
    .
    2.63
    ᡴ
    2.55
     кількість
    2.52
    各样的
    2.44
    毉
    2.42
     in
    2.22
    н
    2.20
    鸶
    2.17
     twofold
    2.16
     This
    2.14
    Activations Density 0.005%

    No Known Activations