© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 12936
    Prev
    Next
    INDEX
    Explanations

    Google Maps URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ام
    1.31
     町
    1.25
     아닙
    1.24
     tercera
    1.22
    QUARE
    1.21
     guerra
    1.21
     ン
    1.20
     ホーム
    1.19
     کوردستان
    1.19
    ARCHITECTURE
    1.18
    POSITIVE LOGITS
    worked
    1.17
     worked
    1.09
     individually
    1.06
    ី
    1.05
     nuances
    1.05
    zied
    1.04
     polished
    1.02
     subsequent
    1.02
    ledes
    1.01
    yser
    1.00
    Activations Density 0.011%

    No Known Activations