© 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. 11359
    Prev
    Next
    INDEX
    Explanations

    larger than life, factor, VIII

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

    The neuron fires on content words that appear as parts of longer compound or technical terms—especially the final elements of hyphenated expressions (e.g. “life” in “larger-than-life”) and key nouns in biomedical names (e.g. “factor” in “von Willebrand factor”).

    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
    complished
    -1.90
    🍻
    -1.80
    commodation
    -1.71
     prega
    -1.70
     departe
    -1.65
     denominada
    -1.63
    🥴
    -1.61
    🤧
    -1.59
    uteurs
    -1.58
     marcato
    -1.57
    POSITIVE LOGITS
    </strong>
    1.88
     that
    1.84
    1
    1.73
    7
    1.70
    5
    1.68
    </h4>
    1.66
    3
    1.54
    2
    1.50
    </b>
    1.49
    1.49
    Activations Density 0.118%

    No Known Activations