© 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. 40-GEMMASCOPE-2-RES-65K
    7. 3994
    Prev
    Next
    INDEX
    Explanations

    dangerous or DAN

    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_40_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
    P
    0.45
    Tá
    0.43
    Ö
    0.42
    各位同學
    0.42
     المستقبل
    0.42
    Pw
    0.41
    唢
    0.41
    scre
    0.41
    毕
    0.40
    abca
    0.40
    POSITIVE LOGITS
    ielle
    0.67
    ियल
    0.62
     dangerous
    0.61
     опас
    0.61
    Dangerous
    0.60
     Dang
    0.58
    dangerous
    0.58
     Dangerous
    0.56
     dangerously
    0.56
     danger
    0.54
    Activations Density 0.042%

    No Known Activations