© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11114
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on terms referring to legal or constitutional rights and protections.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    긱
    0.55
     डैश
    0.54
     déplacements
    0.53
     thefts
    0.53
     हाइट
    0.52
    盆
    0.52
     arrears
    0.51
    糖尿病
    0.50
     prestations
    0.49
    
    0.49
    POSITIVE LOGITS
     Journalism
    2.22
     journalism
    2.06
     Media
    2.00
    Media
    1.95
     journalistic
    1.92
     MEDIA
    1.90
     Journalists
    1.88
     media
    1.88
     Journalist
    1.82
    media
    1.77
    Activations Density 0.315%

    No Known Activations