© 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. 1128
    Prev
    Next
    INDEX
    Explanations

    devil, Satan, Lucifer, Diablo

    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
     dafür
    -0.80
     hafif
    -0.79
    有问题
    -0.77
    은
    -0.77
     entwick
    -0.77
     eseguire
    -0.77
    肿
    -0.75
     giang
    -0.74
    パネル
    -0.71
     världen
    -0.71
    POSITIVE LOGITS
    👹
    1.33
    ishly
    1.32
     Devil
    1.28
    👿
    1.21
    😈
    1.20
     devil
    1.20
    Lucifer
    1.14
    Devil
    1.14
     Lucifer
    1.09
    devil
    1.05
    Activations Density 0.010%

    No Known Activations