© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 12105
    Prev
    Next
    INDEX
    Explanations

    code logic placeholder

    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
    Not in Any Lists

    No Comments

    Negative Logits
    unya
    1.17
     sails
    1.16
     গিয়েছিল
    1.11
    而被
    1.11
     কলকাতায়
    1.10
     revert
    1.08
     bequeathed
    1.06
    ḳ
    1.06
     colours
    1.06
     returned
    1.04
    POSITIVE LOGITS
     Desarrollo
    1.21
     Usual
    1.12
     Обычно
    1.08
    =======
    1.06
     Sim
    1.03
     Cunningham
    1.03
     Watson
    1.02
    ्रिक
    1.02
     Place
    1.00
     Simmons
    1.00
    Activations Density 0.011%

    No Known Activations