© 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. 111069
    Prev
    Next
    INDEX
    Explanations

    price fixing and cartels

    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
     dias
    -0.79
    vaders
    -0.76
    onChange
    -0.76
    oles
    -0.73
    Conne
    -0.73
    cerin
    -0.73
     اکس
    -0.73
    ్
    -0.72
     enam
    -0.71
     (($
    -0.71
    POSITIVE LOGITS
     collusion
    1.85
     coll
    1.82
     cartel
    1.66
     agreement
    1.57
     agreements
    1.48
     coordination
    1.38
     carte
    1.32
     agreed
    1.31
     price
    1.30
     Coll
    1.30
    Activations Density 0.019%

    No Known Activations