© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49027
    Prev
    Next
    INDEX
    Explanations

    former accused of 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
     недавно
    -0.81
    คัญ
    -0.81
     поступа
    -0.80
     pesca
    -0.77
    replaceAll
    -0.77
    iace
    -0.76
     hijab
    -0.75
     especially
    -0.75
     установки
    -0.73
     immaculate
    -0.73
    POSITIVE LOGITS
    alleg
    1.29
     former
    1.23
     corruption
    1.13
    former
    1.12
     suspended
    1.07
     corrupt
    1.06
     alleged
    1.03
     accused
    1.02
    Former
    1.02
     implicated
    1.01
    Activations Density 0.113%

    No Known Activations