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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 2030
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
     actualizar
    1.19
    金额
    1.10
     yanlış
    1.09
    젝
    1.09
     nCmd
    1.08
    Dtls
    1.08
    IFO
    1.06
    铨
    1.06
     ITEM
    1.04
    Demand
    1.03
    POSITIVE LOGITS
     picturesque
    1.94
     canyons
    1.80
    景色
    1.75
     majestic
    1.68
     wildflowers
    1.68
     glistening
    1.67
     breathtaking
    1.67
     gorgeous
    1.63
     lush
    1.63
     splendor
    1.55
    Activations Density 1.416%

    No Known Activations