© 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. 8744
    Prev
    Next
    INDEX
    Explanations

    German, Dutch, Indonesian words

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

    The neuron strongly activates on high‐frequency function and quantifier words (e.g. “us,” “many,” “lots,” “so,” “through,” “used,” etc.) rather than on specific content terms.

    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
    و
    0.91
    prises
    0.79
    efully
    0.77
    tattoo
    0.76
    تك
    0.75
     defies
    0.74
    ت
    0.73
    iexpress
    0.73
    itness
    0.71
    شع
    0.71
    POSITIVE LOGITS
    +}^{
    0.78
     tafel
    0.78
     Dör
    0.76
     Tisch
    0.75
     omgeving
    0.73
     Deutsches
    0.72
     nochmal
    0.71
     abar
    0.70
     schneller
    0.70
     einzel
    0.69
    Activations Density 0.000%

    No Known Activations