© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9162
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on words and phrases expressing legal or constitutional “rights” or protections (e.g. right to free speech, right to choose).

    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_24_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
    د
    0.98
    ع
    0.95
     IDs
    0.86
    URLs
    0.82
     повы
    0.81
    árm
    0.80
    ώντας
    0.80
    ى
    0.79
    ATE
    0.79
     MPs
    0.78
    POSITIVE LOGITS
     rights
    1.48
     freedoms
    1.41
     freedom
    1.36
     Rights
    1.35
     RIGHTS
    1.23
     diritti
    1.20
     liberty
    1.17
     droits
    1.13
    rights
    1.13
     libertà
    1.13
    Activations Density 0.076%

    No Known Activations