© 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. 5574
    Prev
    Next
    INDEX
    Explanations

    numbers and units

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

    The neuron activates on mentions of “kitchen,” i.e. whenever a document refers to having a (fully equipped) kitchen.

    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
    optimized
    0.74
     عناصر
    0.73
     要素
    0.68
    彠
    0.67
     analyzers
    0.67
    ่อ
    0.66
     elementi
    0.64
    ার্স
    0.64
    ้ม
    0.64
     элементы
    0.64
    POSITIVE LOGITS
     extranj
    0.80
     Orwell
    0.76
     Citibank
    0.76
     diciembre
    0.75
     这
    0.74
     bước
    0.74
    。)
    0.73
     Việt
    0.72
     tảo
    0.72
     전쟁
    0.71
    Activations Density 0.001%

    No Known Activations