© 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. 2315
    Prev
    Next
    INDEX
    Explanations

    Milgram obedience experiments

    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
    Werbung
    -0.81
     kwamen
    -0.77
     WRITER
    -0.75
    isele
    -0.75
     Forster
    -0.75
     pintores
    -0.75
    フライ
    -0.71
    रीदारी
    -0.70
    ータス
    -0.70
     ул
    -0.69
    POSITIVE LOGITS
    diffusion
    1.13
     obedience
    1.08
     Obedience
    1.01
     Mil
    0.96
    Mil
    0.94
     experimenter
    0.93
     Compliance
    0.91
    obedience
    0.90
     compliance
    0.89
    Compliance
    0.89
    Activations Density 0.016%

    No Known Activations