© 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. 10078
    Prev
    Next
    INDEX
    Explanations

    how to do something

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

    The neuron is triggered by numeric tokens—especially years, page or volume numbers, and other citation-style numeric references.

    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
    𝓈
    0.86
    細胞
    0.77
     細胞
    0.77
     ஆங்கில
    0.75
     anglais
    0.73
    轟
    0.73
     набу
    0.73
    𝒸
    0.73
    ABASE
    0.71
     ভয়ানক
    0.71
    POSITIVE LOGITS
    RootDir
    0.77
     mil
    0.70
     unmatched
    0.70
    osen
    0.70
    leda
    0.70
    rema
    0.69
     Karab
    0.69
     Sik
    0.68
     maked
    0.68
     kuidas
    0.68
    Activations Density 0.001%

    No Known Activations