© 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. 10638
    Prev
    Next
    INDEX
    Explanations

    certain KPIs, quilt set, stock products, mouse pad, faulty part, Aging materials, Avatar component

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

    The neuron consistently lights up on content-bearing nouns (i.e. substantive words rather than function words).

    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
    T
    0.98
    टी
    0.88
    最
    0.88
    ü
    0.77
    1
    0.75
    7
    0.75
    ف
    0.75
    t
    0.74
    6
    0.73
    哩
    0.73
    POSITIVE LOGITS
     दिर
    0.81
     Materi
    0.78
     timeline
    0.72
     важ
    0.71
     punch
    0.70
     ";
    0.69
    riak
    0.69
     czas
    0.68
     দেরী
    0.68
     Gas
    0.68
    Activations Density 0.000%

    No Known Activations