© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 6896
    Prev
    Next
    INDEX
    Explanations

    whining, complaining, moaning

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

    The neuron fires on words expressing whining or complaining (e.g. “whining,” “whinge,” “moan”).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    摃
    -2.50
     Augenblick
    -2.22
    焄
    -2.09
     there
    -2.02
     sometime
    -1.98
    ?”
    -1.98
     inevitably
    -1.98
    However
    -1.97
    ஂ
    -1.95
     comprised
    -1.91
    POSITIVE LOGITS
    
    2.08
    鸱
    2.02
    뿅
    2.00
    ίες
    1.99
    屺
    1.98
    柃
    1.95
    ꪻ
    1.94
    檍
    1.92
    ίας
    1.91
     telefonu
    1.91
    Activations Density 0.006%

    No Known Activations