© 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. 12306
    Prev
    Next
    INDEX
    Explanations

    firearm, rifle, pistol, jam

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

    The neuron fires on numeric specification tokens—particularly measurements and decimal‐number values indicating sizes, lengths, weights, etc.

    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
    🚕
    0.72
    サル
    0.62
    去世
    0.61
    驱动
    0.60
    驶
    0.58
    🎈
    0.58
     lysosomes
    0.57
    Debug
    0.57
    冰箱
    0.57
    爸爸
    0.56
    POSITIVE LOGITS
     firearm
    1.79
     pistol
    1.74
     firearms
    1.74
     handgun
    1.70
     rifles
    1.67
     pistols
    1.65
     rifle
    1.62
     Firearms
    1.54
     Pistol
    1.53
    銃
    1.47
    Activations Density 0.181%

    No Known Activations