© 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. 5926
    Prev
    Next
    INDEX
    Explanations

    shooting or arrows

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

    The main thing this neuron does is find words describing shooting or firing a weapon.

    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
     swords
    0.80
     sword
    0.77
     Sword
    0.77
    Sword
    0.77
     Swords
    0.74
    sword
    0.63
     blade
    0.60
    鎚
    0.58
     knife
    0.57
    _|
    0.56
    POSITIVE LOGITS
     arrows
    1.76
     arrow
    1.68
    箭
    1.60
     shoot
    1.54
     shooting
    1.54
    arrows
    1.52
     Arrow
    1.51
    Arrow
    1.49
    射
    1.49
     archery
    1.48
    Activations Density 0.151%

    No Known Activations