© 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. 12748
    Prev
    Next
    INDEX
    Explanations

    than a

    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
     فناوری
    1.04
     kỷ
    0.99
    侖
    0.98
    금융
    0.93
     financed
    0.92
     daugiau
    0.91
    лизация
    0.91
    昉
    0.90
     Coke
    0.89
    வதில்
    0.89
    POSITIVE LOGITS
     editable
    1.32
     printable
    1.32
     readme
    1.31
     Printable
    1.26
     Editable
    1.25
    template
    1.23
     beginner
    1.18
     README
    1.18
     downloadable
    1.18
     template
    1.17
    Activations Density 0.297%

    No Known Activations