© 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. 11090
    Prev
    Next
    INDEX
    Explanations

    start white

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

    This neuron detects chemical‐formula patterns, especially H₂O.

    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
    д
    0.90
    п
    0.86
     terletak
    0.78
    Ж
    0.77
     effectué
    0.76
    П
    0.75
    І
    0.75
     가능한
    0.74
    ι
    0.73
     I
    0.71
    POSITIVE LOGITS
     neutrinos
    0.93
     pallets
    0.88
     dioxygen
    0.86
     anions
    0.84
     Drinfeld
    0.84
     prokary
    0.84
    чное
    0.82
     synergies
    0.82
     neutrons
    0.82
     synchrotron
    0.81
    Activations Density 0.000%

    No Known Activations