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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 25885
    Prev
    Next
    INDEX
    Explanations

    official decisions and governance

    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
    tende
    -0.86
     koron
    -0.81
     escolher
    -0.79
     nabo
    -0.79
    nende
    -0.79
    jaj
    -0.77
    Offic
    -0.75
     garda
    -0.74
     stoff
    -0.74
     Ders
    -0.73
    POSITIVE LOGITS
     постанов
    1.02
     Cabinet
    0.99
     resolution
    0.96
     approved
    0.93
     decision
    0.89
    決定
    0.88
     meeting
    0.86
    resolution
    0.85
    Minutes
    0.85
     resolutions
    0.84
    Activations Density 0.011%

    No Known Activations