© 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. 61269
    Prev
    Next
    INDEX
    Explanations

    artificial intelligence and machine learning

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

    This neuron specializes in spotting parenthesized technology acronyms (e.g. “(IoT)”, “(AR)”, “(AI)”).

    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
     one
    -1.95
    because
    -1.85
     with
    -1.68
     three
    -1.52
     when
    -1.48
     two
    -1.48
     because
    -1.45
    However
    -1.44
     these
    -1.41
     specchio
    -1.39
    POSITIVE LOGITS
    metology
    1.55
    кации
    1.46
    欒
    1.41
    に興味
    1.40
    摸了
    1.40
     chegar
    1.38
     และ
    1.36
    踮
    1.34
     dreary
    1.31
    GRAPHY
    1.30
    Activations Density 0.333%

    No Known Activations