© 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. 69450
    Prev
    Next
    INDEX
    Explanations

    dynamic descriptions

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

    The neuron primarily fires on occurrences of the adjective “dynamic.”

    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
    pulseira
    -1.66
    DÉ
    -1.57
     scaricare
    -1.54
    CHRIST
    -1.52
     effetto
    -1.51
    banen
    -1.49
    的主要
    -1.48
    CHARLES
    -1.46
     algún
    -1.45
    噥
    -1.45
    POSITIVE LOGITS
    During
    1.75
    f
    1.65
    He
    1.65
    \
    1.57
    THE
    1.52
     –
    1.50
     और
    1.40
    他在
    1.40
     où
    1.38
     preuve
    1.38
    Activations Density 0.013%

    No Known Activations