© 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. 119268
    Prev
    Next
    INDEX
    Explanations

    MR, FR, SR, PR, IR, XR, JR, WR abbreviations

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

    The neuron strongly responds to uppercase letter sequences—i.e. acronyms or abbreviations (like “FR,” “MR,” “IRS,” “XR” etc.).

    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
    と
    -0.90
     impacted
    -0.89
    жны
    -0.88
     detailed
    -0.87
    fions
    -0.81
     linked
    -0.81
     solito
    -0.78
     none
    -0.78
     PLEASE
    -0.78
     suele
    -0.77
    POSITIVE LOGITS
    ra
    0.93
    Ps
    0.91
    ursue
    0.90
    Beans
    0.87
    tragung
    0.84
    daemon
    0.84
    msup
    0.83
    各式
    0.82
    arry
    0.82
    aimerais
    0.81
    Activations Density 0.058%

    No Known Activations