© 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. 31-GEMMASCOPE-2-RES-16K
    7. 3028
    Prev
    Next
    INDEX
    Explanations

    The neuron detects legal‐style citations and references—especially section numbers, case or witness labels, and other procedural numbering.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    legal and procedural language in formal court documents and testimony.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    language about legal proceedings and judicial procedure, especially discussions of evidence, witnesses, and court examinations.

    oai_token-act-pair · gpt-5Triggered 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
    িবাস
    0.63
     अनाउंस
    0.60
     deve
    0.59
     conquista
    0.59
     anuncia
    0.59
     denomina
    0.59
     rejuven
    0.58
     hydraz
    0.57
     cyclo
    0.56
     promul
    0.56
    POSITIVE LOGITS
     witnesses
    2.06
     witness
    2.03
     testimony
    1.96
     testifying
    1.94
    Witness
    1.91
     testify
    1.81
    witness
    1.80
     Witnesses
    1.78
    証
    1.76
     Testimony
    1.75
    Activations Density 0.447%

    No Known Activations