© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 42263
    Prev
    Next
    INDEX
    Explanations

    state of the art equipment

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

    The neuron activates on mentions of “state-of-the-art” or similarly phrased advanced technical equipment and technology.

    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
     dotyczą
    -1.44
    спасибо
    -1.35
    обзор
    -1.29
     about
    -1.27
    изображение
    -1.26
     any
    -1.26
    источник
    -1.26
     stating
    -1.25
    álva
    -1.24
    пример
    -1.22
    POSITIVE LOGITS
     equipment
    1.39
     The
    1.34
     ainsi
    1.23
     we
    1.18
     vede
    1.16
    m
    1.16
     portable
    1.14
    品牌的
    1.13
     meinem
    1.10
     dieser
    1.09
    Activations Density 0.152%

    No Known Activations