© 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. 55783
    Prev
    Next
    INDEX
    Explanations

    fraud, scams, and corruption

    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
     Thief
    -0.88
    ∖
    -0.87
     comporte
    -0.84
     irreparable
    -0.83
    gania
    -0.82
    -*
    -0.81
     mojej
    -0.81
    endida
    -0.80
    Vk
    -0.79
     Storytelling
    -0.79
    POSITIVE LOGITS
     identity
    1.07
     Medicare
    1.02
    identity
    1.01
     insurance
    0.96
     kick
    0.94
     click
    0.93
     identify
    0.93
     wire
    0.91
     Identity
    0.91
     payroll
    0.91
    Activations Density 0.040%

    No Known Activations