© 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. 10276
    Prev
    Next
    INDEX
    Explanations

    antonym, code, truly

    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
     benöt
    1.15
     portavoz
    1.14
     wyłącznie
    1.12
    믄
    1.11
    세요
    1.09
     érté
    1.09
    ೇ
    1.09
    려면
    1.08
     województ
    1.08
     diciembre
    1.07
    POSITIVE LOGITS
     The
    1.31
     (
    1.15
    The
    1.15
     goat
    1.09
     umbrella
    1.06
     propelled
    1.02
     ا
    1.01
     watching
    1.01
     change
    1.01
     rope
    1.00
    Activations Density 0.048%

    No Known Activations