© 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. 31-GEMMASCOPE-2-RES-16K
    7. 1275
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on the central “head” word of a clause or sentence—typically the main verb or subject that anchors that clause.

    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
     পেয়েছেন
    0.61
     পেয়েছে
    0.59
    看过
    0.59
     पढ़ते
    0.58
     பேசிய
    0.58
     claves
    0.58
     nadal
    0.55
    飨
    0.55
     nuances
    0.55
     drin
    0.55
    POSITIVE LOGITS
     decided
    3.25
     decide
    2.94
     decides
    2.86
    决定
    2.80
     décidé
    2.72
     décide
    2.72
    決定
    2.69
     Decide
    2.66
     decidió
    2.64
     decidido
    2.63
    Activations Density 1.349%

    No Known Activations