© 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. 11210
    Prev
    Next
    INDEX
    Explanations

    p. followed by number or 'X'

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

    The neuron activates on large numerical values—especially statistical measures such as hazard ratios, confidence‐interval bounds, p-values, and other quantitative results.

    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
     jumper
    0.66
    (?)
    0.62
     russia
    0.61
     PN
    0.60
     pn
    0.60
     donde
    0.59
     (?)
    0.59
     mip
    0.58
    これが
    0.57
    (!)
    0.57
    POSITIVE LOGITS
    ίας
    0.63
     Fees
    0.63
     Fernández
    0.62
    သို့
    0.60
    美好的
    0.60
     Automobiles
    0.60
     อาท
    0.59
     Nhiều
    0.59
     Calder
    0.59
     Consumers
    0.59
    Activations Density 0.015%

    No Known Activations