© 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. 31-GEMMASCOPE-2-RES-16K
    7. 8957
    Prev
    Next
    INDEX
    Explanations

    prints, canvas, art

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

    This neuron activates strongly on terms referring to physical art products (e.g., prints, framed/wood prints, wall art).

    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
    arl
    0.58
    <h2>
    0.57
    調べ
    0.55
     программи
    0.54
    ኪ
    0.54
    介绍了
    0.54
    াপিত
    0.54
    стро
    0.53
     كريم
    0.53
    ನ್ಯ
    0.53
    POSITIVE LOGITS
     Gó
    0.54
     aren
    0.54
    檴
    0.52
     Coats
    0.52
     Donner
    0.51
     பற
    0.51
     PAGES
    0.51
     revest
    0.51
    ">&#
    0.50
    炇
    0.50
    Activations Density 0.001%

    No Known Activations