© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47580
    Prev
    Next
    INDEX
    Explanations

    disregard rules and morals

    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_34/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
    씩
    -0.96
    殓
    -0.84
     ].
    -0.81
     siè
    -0.81
     الشم
    -0.81
     Doh
    -0.79
     texinfo
    -0.79
    ﹕
    -0.78
    忍不住
    -0.77
    けない
    -0.77
    POSITIVE LOGITS
     rules
    1.94
     ethics
    1.62
    rules
    1.61
     logic
    1.60
     considerations
    1.52
     consequences
    1.51
     anything
    1.45
     morals
    1.42
     constraints
    1.39
     morality
    1.39
    Activations Density 0.049%

    No Known Activations