© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 31254
    Prev
    Next
    INDEX
    Explanations

    Satan, Lucifer, demons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     изменений
    0.45
     transfusion
    0.45
     peroxidation
    0.44
     println
    0.43
     уско
    0.43
     TRANSM
    0.43
     transf
    0.42
     酸
    0.42
     perfusion
    0.42
     bleed
    0.41
    POSITIVE LOGITS
     الشيطان
    0.68
     شیطان
    0.66
     Satan
    0.63
     devil
    0.62
     Devil
    0.61
    devil
    0.60
    Devil
    0.57
     satan
    0.55
     devils
    0.52
     Lucifer
    0.47
    Activations Density 0.049%

    No Known Activations