© 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. 22-GEMMASCOPE-RES-131K
    7. 39351
    Prev
    Next
    INDEX
    Explanations

    abbreviation expansion

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

    The neuron is triggered by uppercase abbreviations or initialisms (multi‐letter acronyms) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     доступа
    -1.09
    似乎
    -1.09
     unn
    -1.07
     enraged
    -1.05
     joyful
    -1.02
     的
    -1.02
     señaló
    -1.02
    ᵖ
    -1.02
     arşivlendi
    -1.01
     joyous
    -1.01
    POSITIVE LOGITS
     (
    2.33
     or
    1.20
     (“
    1.15
     yani
    1.10
     -
    1.10
     so
    1.05
     any
    1.05
     Regardless
    1.05
     abbreviation
    1.02
     While
    1.01
    Activations Density 0.136%

    No Known Activations