© 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. 22-GEMMASCOPE-RES-131K
    7. 25061
    Prev
    Next
    INDEX
    Explanations

    legal cases and official titles

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

    The neuron strongly activates on uppercase legal party or organization names (e.g. parties like “Defendant,” “UNITED STATES,” “The People,” and capitalized entity names).

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     tadi
    -1.09
     mär
    -1.05
     such
    -1.05
     läs
    -1.03
     Campeonato
    -1.02
    ָל
    -1.02
    𝙷
    -1.02
     romantis
    -1.02
     bä
    -0.98
    ᅨ
    -0.97
    POSITIVE LOGITS
     later
    1.24
    𝕠
    0.92
     rů
    0.89
    bondale
    0.89
    阙
    0.88
     geöffnet
    0.85
     subsequent
    0.85
     geest
    0.84
     reliance
    0.83
     posteriormente
    0.82
    Activations Density 0.000%

    No Known Activations