© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13903
    Prev
    Next
    INDEX
    Explanations

    weapons and destruction

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

    The neuron strongly activates on mentions of weapons, firearms, and other combat or violent tools (e.g. “weapon,” “rifle,” “steel,” “cutting,” “fire”).

    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
     বাধ্যতামূলক
    0.86
    saving
    0.82
     आव्हान
    0.80
    それでも
    0.77
     bądź
    0.76
    갇
    0.76
    갚
    0.75
    仕方
    0.74
     فوټبال
    0.74
    stven
    0.74
    POSITIVE LOGITS
     Firearms
    1.19
     weapons
    1.10
     weaponry
    1.08
    🔫
    1.02
     firearms
    0.99
     оружи
    0.98
     handgun
    0.96
     pistola
    0.95
     pistol
    0.94
     firearm
    0.90
    Activations Density 2.396%

    No Known Activations