© 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. 8464
    Prev
    Next
    INDEX
    Explanations

    legal verdict

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

    The neuron strongly activates on occurrences of “verdict” (and its variants), i.e. mentions of court‐issued decisions.

    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
    
    -2.73
     \&
    -2.67
     \_
    -2.59
     besonders
    -2.47
     reformas
    -2.39
     guerras
    -2.38
    鱟
    -2.34
     процессы
    -2.33
    灃
    -2.33
    躂
    -2.31
    POSITIVE LOGITS
    .
    4.47
     
    2.92
    R
    2.91
    But
    2.63
    B
    2.58
    2
    2.56
    F
    2.55
    to
    2.47
    事も
    2.44
    0
    2.28
    Activations Density 0.002%

    No Known Activations