© 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. 63663
    Prev
    Next
    INDEX
    Explanations

    violating laws or rules

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron responds to words indicating breaches or violations of rules, laws, or regulations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    FORCE
    -0.96
     모두
    -0.94
    全て
    -0.89
    oosevelt
    -0.88
    arv
    -0.86
     influences
    -0.85
     EXERCISE
    -0.83
     φα
    -0.83
     FORCE
    -0.83
     experiences
    -0.83
    POSITIVE LOGITS
     regulations
    1.23
     norms
    1.22
     curfew
    1.18
     rules
    1.13
    rules
    1.09
     confidentiality
    1.06
     our
    1.04
     by
    1.02
     honnête
    0.96
     ethics
    0.96
    Activations Density 0.029%

    No Known Activations