© 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. 70851
    Prev
    Next
    INDEX
    Explanations

    nature of

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

    The neuron fires on occurrences of the abstract noun “nature” when used in common fixed expressions (e.g. “the nature of …,” “by their nature,” “its very nature”).

    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
    </i>
    -1.77
     a
    -1.59
     myce
    -1.34
    платье
    -1.27
    陨
    -1.23
    饜
    -1.21
    知らせ
    -1.21
    itisation
    -1.13
     потребуется
    -1.12
    </b>
    -1.11
    POSITIVE LOGITS
     размеры
    1.45
     головы
    1.42
    比起
    1.41
     nadzieję
    1.30
     следующий
    1.30
     enviada
    1.30
     circumstances
    1.29
     orgánica
    1.27
    }]{
    1.27
     Antrag
    1.25
    Activations Density 0.059%

    No Known Activations