© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 117913
    Prev
    Next
    INDEX
    Explanations

    parliamentary assembly debate

    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
     goreng
    -0.77
    disposing
    -0.77
     multip
    -0.73
    ;->
    -0.73
    美丽的
    -0.72
    heureux
    -0.72
     éco
    -0.71
     Unidas
    -0.70
     négoci
    -0.70
     takže
    -0.69
    POSITIVE LOGITS
     Parliament
    1.43
     House
    1.40
     parliament
    1.38
     Speaker
    1.38
     debate
    1.37
     motion
    1.24
     parliamentary
    1.22
    Speaker
    1.17
     sitting
    1.16
     парла
    1.15
    Activations Density 0.010%

    No Known Activations