© 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. 10428
    Prev
    Next
    INDEX
    Explanations

    Korean, Berger, art, function

    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
    lact
    1.37
     "|
    1.27
     एले
    1.27
     लोकतंत्र
    1.26
    zata
    1.25
     đựng
    1.25
    catalyzed
    1.24
    acz
    1.23
     '?
    1.23
     مكتب
    1.23
    POSITIVE LOGITS
     벗
    1.21
     Sons
    1.13
    Bsky
    1.13
    そのため
    1.08
     Pasand
    1.05
     Being
    1.03
     Bein
    1.01
     Breaking
    1.01
    써
    0.99
     unfortunately
    0.99
    Activations Density 0.001%

    No Known Activations