© 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. 24-GEMMASCOPE-2-RES-16K
    7. 3656
    Prev
    Next
    INDEX
    Explanations

    listing items or terms

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

    The neuron fires on nouns naming concrete features, amenities, or attractions (e.g. kitchen, bedroom, bathrooms, hot tub, show, mocha, seasons, cover, film).

    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
     materialistic
    0.79
     pois
    0.71
    த்தினை
    0.66
     periodical
    0.66
     todays
    0.65
     سواء
    0.65
    towards
    0.65
     spontaneous
    0.64
     existent
    0.64
    raccoon
    0.64
    POSITIVE LOGITS
    했고
    0.89
    르고
    0.88
     but
    0.80
     Đế
    0.80
    but
    0.78
     ۽
    0.77
    但
    0.77
    른
    0.77
    $,
    0.77
    지만
    0.77
    Activations Density 0.122%

    No Known Activations