© 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. 34-GEMMASCOPE-RES-131K
    4. 50019
    Prev
    Next
    INDEX
    Explanations

    next generation

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

    The neuron fires strongly on mentions of “next-generation” (and related forward-looking technology phrases) 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_34/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
     ricordare
    -0.77
     seguente
    -0.77
    monių
    -0.75
    tilizer
    -0.73
    anthemum
    -0.72
     successivamente
    -0.70
     angegebenen
    -0.70
    BDA
    -0.70
    嬉しい
    -0.69
    もとも
    -0.68
    POSITIVE LOGITS
     generation
    5.56
    generation
    4.06
     génération
    3.61
     Generation
    3.47
     generación
    3.45
    Generation
    3.42
     geração
    3.06
     GENERATION
    2.97
     generazione
    2.61
     generations
    2.50
    Activations Density 0.044%

    No Known Activations