© 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. 12406
    Prev
    Next
    INDEX
    Explanations

    essential goods, raw materials, important biomarkers

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

    The neuron chiefly fires on numeric expressions—especially decimal measurements and statistical counts.

    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
    ruption
    0.79
    quiry
    0.69
    ligence
    0.68
     mentorship
    0.67
    urney
    0.67
    oughby
    0.66
    atelier
    0.66
    donation
    0.66
    platz
    0.65
    trials
    0.65
    POSITIVE LOGITS
     vitamins
    0.94
     hydrocarbons
    0.91
     foodstuffs
    0.91
    某些
    0.90
     carbohydrates
    0.89
     certains
    0.89
     важней
    0.87
     vitamine
    0.86
     lipids
    0.84
     lubricants
    0.83
    Activations Density 0.830%

    No Known Activations