© 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. 24-GEMMASCOPE-2-RES-16K
    7. 9244
    Prev
    Next
    INDEX
    Explanations

    political unrest and violence

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

    The neuron strongly responds to references to Islamist extremist organizations or militant groups (e.g. “al-Qaeda,” “Hamas,” “Islamic State”) and related conflict contexts.

    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
     delightfully
    0.89
     whopping
    0.85
     slotted
    0.84
    丽
    0.84
    痊
    0.82
     dainty
    0.82
    ędzie
    0.81
    垫
    0.80
    娓
    0.79
     satin
    0.78
    POSITIVE LOGITS
     terrorists
    1.73
     extremist
    1.72
     terrorist
    1.70
     Islamist
    1.63
     extremists
    1.62
     insurgents
    1.62
     militants
    1.61
     терро
    1.57
     thugs
    1.56
     সন্ত্রাসী
    1.55
    Activations Density 0.441%

    No Known Activations