© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 2444
    Prev
    Next
    INDEX
    Explanations

    acronym and abbreviation definitions

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

    The neuron responds specifically to uppercase initialisms and acronyms.

    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
    asantry
    -0.83
    loroethane
    -0.79
     convaincre
    -0.79
    artamento
    -0.78
    ervous
    -0.77
     cazul
    -0.77
    ioneta
    -0.75
     termasuk
    -0.75
     Doğ
    -0.75
     tonight
    -0.75
    POSITIVE LOGITS
     stands
    3.92
     acronym
    3.64
     abbreviation
    3.17
    stands
    2.95
     Stands
    2.91
     acronyms
    2.36
     står
    2.34
     steht
    2.28
     abbreviations
    2.17
     stand
    2.16
    Activations Density 0.099%

    No Known Activations