© 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. 11417
    Prev
    Next
    INDEX
    Explanations

    conflict and tension escalation

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

    The neuron strongly activates on formal, “hard‐news” vocabulary—especially policy- and politics-related nominalizations (e.g. trial, criticism, exploration, resignation) characteristic of serious news reporting.

    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
    !
    0.86
     stupid
    0.78
    我们需要
    0.78
     (
    0.76
     (!)
    0.75
     our
    0.74
     আমাদেরকে
    0.71
     we
    0.68
     demain
    0.67
    1
    0.66
    POSITIVE LOGITS
     tensión
    0.89
     amid
    0.88
     tensions
    0.84
    之际
    0.83
     तनाव
    0.82
     TouchUtils
    0.81
     brimming
    0.81
     invigor
    0.79
     increasingly
    0.79
     embold
    0.79
    Activations Density 0.108%

    No Known Activations