© 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. 83329
    Prev
    Next
    INDEX
    Explanations

    difficult experiences and suffering

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

    The neuron selectively fires on semantically rich, open‐class content words (especially nouns, verbs, and adjectives) that carry the “meat” of a narrative or factual report, distinguishing them from common function words.

    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
    ilmente
    -1.02
     apie
    -0.89
     falle
    -0.89
    ิจ
    -0.88
    ômetro
    -0.87
     eulogy
    -0.85
     掃除
    -0.85
    fa
    -0.85
     quoque
    -0.82
    ياء
    -0.81
    POSITIVE LOGITS
     ordeal
    2.80
     nightmare
    2.42
     hell
    2.27
     experience
    2.19
     experiences
    1.82
    nightmare
    1.78
     Hell
    1.74
    Hell
    1.66
     experiencia
    1.64
    experience
    1.63
    Activations Density 0.043%

    No Known Activations