© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 6939
    Prev
    Next
    INDEX
    Explanations

    malpractice and compensation cases

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

    The neuron fires on legal‐liability and compensation keywords (e.g. “malpractice,” “compensation,” “indemnity”).

    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
    strategia
    -1.87
    </h3>
    -1.86
    '
    -1.83
    蘩
    -1.74
    ка
    -1.74
     implementar
    -1.66
     dieß
    -1.64
     reposo
    -1.63
    ,
    -1.60
    ——-
    -1.59
    POSITIVE LOGITS
    </sup>
    2.89
    咦
    2.14
    }$
    2.09
     malpractice
    2.05
    ');
    1.89
    while
    1.88
    ="
    1.84
     Veteran
    1.77
    V
    1.76
    喈
    1.76
    Activations Density 0.004%

    No Known Activations