© 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. 10-GEMMASCOPE-RES-131K
    7. 66208
    Prev
    Next
    INDEX
    Explanations

    Satan and devil references

    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_10/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
    原标题
    -1.90
    onymus
    -1.77
     Anſ
    -1.67
    翃
    -1.64
    tradu
    -1.64
    腚
    -1.61
    豋
    -1.61
    andowski
    -1.59
     界
    -1.58
    I
    -1.57
    POSITIVE LOGITS
     It
    2.16
    秾
    1.90
    
    1.70
     she
    1.65
     There
    1.61
    vrigt
    1.59
     if
    1.56
     في
    1.55
     カ
    1.54
    вості
    1.54
    Activations Density 0.005%

    No Known Activations