© 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. 101705
    Prev
    Next
    INDEX
    Explanations

    acronym explanations

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

    opening parentheses that introduce acronym definitions or expansions.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron detects parenthesized uppercase abbreviations or 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_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
    纛
    -1.48
    
    -1.48
    aphthalene
    -1.45
    transportation
    -1.43
    .\\
    -1.39
    intake
    -1.38
     siguiente
    -1.36
    λους
    -1.33
     everyone
    -1.32
     सभी
    -1.32
    POSITIVE LOGITS
     режима
    1.62
     but
    1.59
    </h3>
    1.52
     potuto
    1.52
    //
    1.42
    IN
    1.39
    ーす
    1.39
     också
    1.38
     This
    1.34
    これも
    1.34
    Activations Density 0.068%

    No Known Activations