© 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. 10529
    Prev
    Next
    INDEX
    Explanations

    not born of flesh nor mortal hand

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

    This neuron detects numeric tokens representing precise quantities—especially multi‐digit or floating‐point numbers.

    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
     сексуа
    1.04
     Stimmung
    0.84
     preoccup
    0.83
     unsurprisingly
    0.82
    adorable
    0.81
     kawaii
    0.81
     frequentemente
    0.80
     :/
    0.79
    🍬
    0.79
     bekommt
    0.78
    POSITIVE LOGITS
     hickory
    0.78
    습니까
    0.70
    秉
    0.70
     gentlemen
    0.70
     integrity
    0.68
     statesmen
    0.68
     dilaksanakan
    0.67
     seven
    0.65
    7
    0.65
     generations
    0.64
    Activations Density 0.003%

    No Known Activations