© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 5707
    Prev
    Next
    INDEX
    Explanations

    resolution of conflict

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

    This neuron detects formal legal procedural language—especially mentions of rights, decisions, and deadlines (e.g. “object within X days,” “decision will take place,” etc.).

    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
     peligros
    0.61
     giao
    0.60
    новним
    0.59
     अलर्ट
    0.59
     circulación
    0.57
     pushedAt
    0.57
     sincron
    0.57
     साझेदारी
    0.55
     ottim
    0.55
     MQTT
    0.54
    POSITIVE LOGITS
     arbitration
    1.62
     Arbitration
    1.51
     arbitrator
    1.51
     mediation
    1.41
     Dispute
    1.34
     Mediation
    1.34
     Disputes
    1.31
     hearings
    1.27
     adjudication
    1.26
     arbit
    1.25
    Activations Density 0.372%

    No Known Activations