© 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. 12955
    Prev
    Next
    INDEX
    Explanations

    language, code, versions

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

    The neuron is highly responsive to numeric and quantity expressions—digits, number words (“one,” “6,” “lots,” etc.) and other tokens that signal counts or measurements.

    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
    theless
    0.89
    hcim
    0.83
    वरों
    0.77
    י
    0.77
    hiddenMap
    0.77
    reportBody
    0.76
    푞
    0.76
     ovat
    0.76
    分的
    0.75
    sonaro
    0.74
    POSITIVE LOGITS
     traceback
    0.70
    0.68
     buffering
    0.68
     UIImage
    0.66
    </h3>
    0.66
     trait
    0.66
     plaid
    0.66
     Unsupported
    0.65
     après
    0.64
    los
    0.63
    Activations Density 0.001%

    No Known Activations