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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 15252
    Prev
    Next
    INDEX
    Explanations

    e-commerce

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
     stratigraphic
    0.53
    otrich
    0.52
     खिला
    0.52
     SwitchCompat
    0.52
    を入力
    0.51
    )})
    0.50
     位置
    0.50
     ዘ
    0.50
    となっています
    0.50
     уйный
    0.49
    POSITIVE LOGITS
     commerce
    1.54
     Commerce
    1.45
    commerce
    1.43
    Commerce
    1.30
     eCommerce
    1.11
     comercio
    1.04
     e
    1.00
     ecommerce
    0.99
    ecommerce
    0.92
     Comercio
    0.87
    Activations Density 0.035%

    No Known Activations