© 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. 65482
    Prev
    Next
    INDEX
    Explanations

    historic province, was built, was listed

    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
     arbejds
    -0.93
     stoff
    -0.93
     lokale
    -0.92
     pæ
    -0.84
     vertus
    -0.84
     PHILOSOPHY
    -0.83
    脐
    -0.83
    suddenly
    -0.82
     billeder
    -0.82
     feitos
    -0.82
    POSITIVE LOGITS
     farms
    0.90
     farm
    0.86
    zeum
    0.80
    ungkinan
    0.80
    cipar
    0.79
    場所
    0.79
    時代
    0.79
     schreibt
    0.78
    シング
    0.77
     WTO
    0.77
    Activations Density 0.084%

    No Known Activations