© 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
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 32769
    Prev
    Next
    INDEX
    Explanations

    Satan, Devil, Lucifer

    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_16_width_262k_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
    ný
    0.65
    čné
    0.64
    nię
    0.62
    მასრულ
    0.61
    žiť
    0.59
    テイン
    0.59
    স
    0.59
    ných
    0.59
    せ
    0.59
     INR
    0.59
    POSITIVE LOGITS
     Satan
    0.88
     Devil
    0.69
     الشيطان
    0.64
     devil
    0.61
     Devils
    0.61
     agents
    0.56
     devils
    0.55
    g
    0.55
    он
    0.55
     satan
    0.54
    Activations Density 0.013%

    No Known Activations