© 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. 8717
    Prev
    Next
    INDEX
    Explanations

    management system

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

    The neuron fires on numeric tokens representing measurement values or citation‐style numbers (e.g., floating‐point or large integers).

    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
    ner
    0.70
    </sup>
    0.69
    
    0.69
     Kang
    0.66
    grab
    0.65
    トン
    0.65
    obes
    0.65
     foto
    0.64
    it
    0.64
    et
    0.64
    POSITIVE LOGITS
    新生
    0.92
     happenings
    0.91
     traffickers
    0.89
     polynucle
    0.89
     жителей
    0.87
    жета
    0.86
    骼
    0.84
     neutrinos
    0.82
     thugs
    0.82
     dichloromethane
    0.82
    Activations Density 0.000%

    No Known Activations