© 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. 34-GEMMASCOPE-RES-131K
    7. 102997
    Prev
    Next
    INDEX
    Explanations

    gulp and nervousness

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

    This neuron is keyed to first-person self-references—that is, words like “I,” “me,” and personal utterances (“Me:”, “let me,” etc.) in a narrative context.

    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
    龇
    -0.94
    Patience
    -0.91
     disappointment
    -0.90
    ématique
    -0.88
     disappointed
    -0.87
     annoyance
    -0.83
     surprised
    -0.82
     frustra
    -0.82
    osd
    -0.82
     frustration
    -0.82
    POSITIVE LOGITS
     gulp
    2.08
     nervously
    1.96
     gul
    1.82
     fear
    1.81
     panic
    1.76
    gulp
    1.74
     nervous
    1.63
     swallowed
    1.55
     swallow
    1.52
     trembling
    1.50
    Activations Density 0.006%

    No Known Activations