© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91615
    Prev
    Next
    INDEX
    Explanations

    appellate court division

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Least
    -0.77
     Huguen
    -0.74
     الأكثر
    -0.73
    擦
    -0.71
     рисунок
    -0.71
     Khalil
    -0.70
     separately
    -0.69
     trening
    -0.69
    serious
    -0.69
    lished
    -0.69
    POSITIVE LOGITS
    getApp
    1.02
     getApp
    1.01
     App
    0.91
     apparition
    0.85
    うさぎ
    0.84
     iklan
    0.79
     Ap
    0.76
    Kart
    0.76
    zej
    0.76
    baum
    0.75
    Activations Density 0.080%

    No Known Activations