© 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. 12562
    Prev
    Next
    INDEX
    Explanations

    weapons and combat

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

    The neuron fires on language describing parkour or obstacle-course–style physical movement (e.g. training, traversing, jumping, climbing through challenges).

    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
     Montessori
    0.83
     Fairy
    0.77
     fairy
    0.73
    🎠
    0.72
    🧚
    0.67
    🦄
    0.65
     fairies
    0.63
    fairy
    0.63
     Disney
    0.62
     disney
    0.61
    POSITIVE LOGITS
     badass
    1.25
     Sniper
    1.16
     SWAT
    1.13
     sniper
    1.11
     shootout
    1.09
     gunmen
    1.07
    🔫
    1.05
     gunman
    1.05
     pistol
    1.02
    銃
    1.02
    Activations Density 0.477%

    No Known Activations