© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 13613
    Prev
    Next
    INDEX
    Explanations

    evilness and maliciousness

    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_53_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
    岌
    0.42
    잦
    0.40
     einger
    0.39
    蛍
    0.39
    ႁ
    0.38
    ⵃ
    0.38
     დაკ
    0.37
    ាត់
    0.37
     Informal
    0.37
    名人
    0.37
    POSITIVE LOGITS
     evil
    3.69
     Evil
    3.20
    Evil
    3.20
    evil
    3.06
     зло
    2.83
     악
    2.70
    悪
    2.56
    恶
    2.52
    惡
    2.50
    邪
    2.47
    Activations Density 0.074%

    No Known Activations