© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92786
    Prev
    Next
    INDEX
    Explanations

    war crimes and former leaders

    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
     Aktu
    -0.77
    custo
    -0.74
    枷
    -0.73
    classmethod
    -0.72
    tinger
    -0.71
     rigorous
    -0.69
     būt
    -0.69
     darbu
    -0.68
    支部
    -0.67
    称号
    -0.67
    POSITIVE LOGITS
    ühren
    0.89
     supernova
    0.85
    Former
    0.82
     command
    0.82
    ICC
    0.82
    打造
    0.82
    Command
    0.81
    cière
    0.81
    ılıyor
    0.80
     Yoo
    0.80
    Activations Density 0.039%

    No Known Activations