© 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. 41812
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations

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

    The neuron fires on mentions of the term “acronym” (and its close variants such as “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_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
    分か
    -1.60
    .
    -1.55
     even
    -1.50
    驸
    -1.45
    mė
    -1.45
    да
    -1.45
    <bos>
    -1.43
    assertSame
    -1.40
    corrhi
    -1.37
     only
    -1.36
    POSITIVE LOGITS
     they
    2.11
    3
    1.79
    ’
    1.69
     niedersachsen
    1.60
     acronym
    1.59
     valentín
    1.56
     Longer
    1.52
    ↵
    1.48
    驺
    1.48
     córdoba
    1.47
    Activations Density 0.028%

    No Known Activations