© 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. 10-GEMMASCOPE-RES-131K
    7. 130661
    Prev
    Next
    INDEX
    Explanations

    two letter abbreviations for acronyms

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

    The neuron fires on isolated uppercase acronym or abbreviation tokens (short sequences of capital letters).

    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
    ={()=>
    -1.30
     satisfactor
    -1.27
     顔
    -1.23
     participaron
    -1.20
     dará
    -1.19
     your
    -1.17
    และ
    -1.16
    khid
    -1.16
     víc
    -1.12
     Procure
    -1.11
    POSITIVE LOGITS
     a
    1.46
     ambos
    1.26
     murni
    1.17
    6
    1.16
     diciembre
    1.15
    fordshire
    1.13
     neue
    1.13
    7
    1.13
     în
    1.13
    ronomy
    1.12
    Activations Density 0.173%

    No Known Activations