© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 10249
    Prev
    Next
    INDEX
    Explanations

    federal forces

    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
    .^
    1.15
     herein
    1.12
    </caption>
    1.06
     (\$
    1.04
     \|
    1.02
     plotted
    1.02
     uttering
    1.01
     $\|
    1.00
    fle
    1.00
     €
    0.99
    POSITIVE LOGITS
     filho
    1.40
     mamá
    1.40
     popolo
    1.39
     dernier
    1.38
     cuarta
    1.38
    ultimo
    1.36
     hijo
    1.34
     potere
    1.33
     diventare
    1.31
     sklep
    1.31
    Activations Density 0.004%

    No Known Activations