© 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. 62923
    Prev
    Next
    INDEX
    Explanations

    enforcement of laws and mandates

    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
    ībā
    -0.90
    lillah
    -0.82
     muffin
    -0.81
    čené
    -0.81
     estabilidad
    -0.81
     Kashi
    -0.81
     kingdoms
    -0.79
    tetur
    -0.78
    eling
    -0.77
    หรับ
    -0.77
    POSITIVE LOGITS
     enforcement
    5.22
     enforce
    4.09
    enforcement
    4.06
     enforcing
    3.94
     Enforcement
    3.77
    Enforcement
    3.72
     enforced
    3.08
    enforce
    2.95
    FORCEMENT
    2.25
     enforceable
    2.14
    Activations Density 0.050%

    No Known Activations