© 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. 12852
    Prev
    Next
    INDEX
    Explanations

    including / especially

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

    The neuron fires on specialized technical jargon, especially file‐format and product‐feature terms (e.g. “TIFF,” “searchable PDF,” “comprehensive annotation capabilities”).

    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
    พวกเขา
    0.74
     พวก
    0.72
    他们在
    0.69
    他们的
    0.68
    它们的
    0.68
    उनके
    0.65
    उनकी
    0.64
    这些
    0.63
    Their
    0.63
    พวก
    0.61
    POSITIVE LOGITS
     dichotomy
    0.73
     быть
    0.71
     oneself
    0.66
     ggplot
    0.63
     acuity
    0.63
     essere
    0.63
     JESUS
    0.63
     olması
    0.63
     sufficiency
    0.63
     PubMed
    0.63
    Activations Density 0.159%

    No Known Activations