© 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. 34-GEMMASCOPE-RES-131K
    7. 30116
    Prev
    Next
    INDEX
    Explanations

    court and legal cases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    উ
    -0.78
    ρισ
    -0.78
     mencionó
    -0.76
     थे
    -0.76
    lış
    -0.75
    iarkan
    -0.75
     Simeon
    -0.71
    に座
    -0.70
     pouvons
    -0.70
     $('#
    -0.70
    POSITIVE LOGITS
    ების
    0.79
    什么呢
    0.71
     均
    0.65
     reloj
    0.65
     lin
    0.65
     cara
    0.65
     máximo
    0.64
    醸
    0.64
    oga
    0.63
     Allerdings
    0.62
    Activations Density 0.046%

    No Known Activations