© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6274
    Prev
    Next
    INDEX
    Explanations

    python collections module

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

    The neuron fires strongly on the word “collection,” especially in contexts referring to picture or gallery collections.

    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_31_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
     Soak
    0.58
     postId
    0.53
    hnt
    0.52
     ！
    0.52
    ental
    0.50
    ignano
    0.50
     getInstance
    0.50
     プラス
    0.49
     Vamos
    0.49
     합
    0.49
    POSITIVE LOGITS
    兴趣
    0.63
     groupings
    0.61
    興趣
    0.61
    週期
    0.60
    ouncements
    0.59
     announcements
    0.58
     collections
    0.57
     ilgi
    0.57
    興味
    0.56
    一组
    0.56
    Activations Density 0.000%

    No Known Activations