© 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. 110866
    Prev
    Next
    INDEX
    Explanations

    important followed by qualifier

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

    The main thing this neuron does is detect occurrences of the word “important.”

    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
     to
    -1.91
    ౭
    -1.77
     instead
    -1.70
    encies
    -1.67
     seulement
    -1.63
    蟊
    -1.59
     actual
    -1.57
    <i>
    -1.57
    colección
    -1.52
    ᯾
    -1.52
    POSITIVE LOGITS
    </em>
    2.34
    </h4>
    2.00
     costuras
    1.75
    今では
    1.75
     setelah
    1.70
    当時は
    1.65
    Гля
    1.62
    雋
    1.61
     після
    1.61
    Чита
    1.60
    Activations Density 0.035%

    No Known Activations