© 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. 45663
    Prev
    Next
    INDEX
    Explanations

    convincing and persuasive statements

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

    The neuron activates on occurrences of “convince”-derived words (e.g. convincing, convincingly, credible/persuasive).

    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
    ?
    -2.16
    ]
    -2.06
    -
    -1.89
     meravigli
    -1.88
     \'
    -1.84
    可以
    -1.84
    
    -1.77
     プリント
    -1.77
     about
    -1.71
     ``
    -1.71
    POSITIVE LOGITS
    あります
    2.03
     inventive
    1.91
    藹
    1.81
    Итог
    1.78
    塒
    1.72
    زيل
    1.70
    ﾈ
    1.65
    ซึ่ง
    1.63
     です
    1.62
     makeshift
    1.62
    Activations Density 0.003%

    No Known Activations