© 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. 12269
    Prev
    Next
    INDEX
    Explanations

    mathematical C++ code

    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
     navegador
    1.09
     bør
    1.09
    byte
    1.04
     Además
    0.99
    <eos>
    0.99
     Sein
    0.99
    Ele
    0.98
     skriver
    0.97
    Además
    0.97
    Vie
    0.94
    POSITIVE LOGITS
     competitiveness
    1.15
     효
    1.12
     Meadows
    1.05
     Beers
    1.03
    AcOH
    1.03
    )}}\
    1.02
     MeOH
    1.01
    -‘
    1.01
    ‵
    1.00
    ヮ
    0.99
    Activations Density 0.001%

    No Known Activations