© 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. 7609
    Prev
    Next
    INDEX
    Explanations

    summarize, categorize, sentiment

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

    The neuron fires on content-bearing nouns that name specific subjects, categories, or technical variables.

    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
    ,
    0.82
    /
    0.77
    ;
    0.69
    4
    0.65
    :
    0.63
    //#
    0.62
     Daughter
    0.62
     daughter
    0.61
     trapped
    0.59
     -
    0.59
    POSITIVE LOGITS
     dataframe
    1.03
     dataset
    0.92
     datasets
    0.91
     ggplot
    0.89
     gegevens
    0.88
    ข้อมูล
    0.86
     maatau
    0.85
     डेटा
    0.83
     بيانات
    0.83
     údaje
    0.82
    Activations Density 0.100%

    No Known Activations