© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9427
    Prev
    Next
    INDEX
    Explanations

    Netflix availability and changes

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

    This neuron fires strongly on content-heavy nouns or fixed noun phrases (e.g. “top coat,” “botanic gardens,” “link-building abuse”), i.e. words naming key entities or topics.

    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
     Engineered
    0.89
     nginx
    0.83
     практике
    0.82
    岖
    0.82
     сказала
    0.81
     Также
    0.80
    스타그램
    0.79
    neapolis
    0.78
    くん
    0.77
     королев
    0.77
    POSITIVE LOGITS
    র
    0.92
    di
    0.82
    मध्ये
    0.81
     tranch
    0.80
    wide
    0.77
    icans
    0.72
    byn
    0.72
    标签
    0.70
    là
    0.70
    ഡി
    0.69
    Activations Density 0.000%

    No Known Activations