© 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. 102583
    Prev
    Next
    INDEX
    Explanations

    international law enforcement

    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
    Army
    -0.77
    üssel
    -0.76
    Aquí
    -0.72
     תוכ
    -0.70
    끔
    -0.69
     conspira
    -0.68
    GPL
    -0.68
    Essay
    -0.68
    ytick
    -0.68
    huo
    -0.67
    POSITIVE LOGITS
     Interpol
    2.03
     INTER
    1.68
     Интер
    1.31
    INTER
    1.30
     interpol
    1.27
     Eu
    1.08
    打击
    0.90
     Redding
    0.88
    interpolate
    0.83
     ICA
    0.82
    Activations Density 0.019%

    No Known Activations