© 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. 82910
    Prev
    Next
    INDEX
    Explanations

    news agency wire

    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
    Imprimir
    -0.85
     Daimler
    -0.81
    INTEGR
    -0.78
    Personne
    -0.77
    Thiết
    -0.75
     superstars
    -0.74
    hdd
    -0.71
    Beef
    -0.71
      [
    -0.71
     Wheatley
    -0.70
    POSITIVE LOGITS
     agency
    3.20
     wire
    2.64
    agency
    2.55
     Agency
    2.52
    Agency
    2.38
     news
    2.20
     agencies
    2.19
     AGENCY
    2.13
    wire
    1.96
     Agencies
    1.89
    Activations Density 0.029%

    No Known Activations