© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9927
    Prev
    Next
    INDEX
    Explanations

    simple, area, types

    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
    워서
    1.15
    噬
    1.15
    bmc
    1.09
     reconcile
    1.06
     spoil
    1.06
    thrombin
    1.06
    和大
    1.06
     execute
    1.05
    繭
    1.04
    還可以
    1.03
    POSITIVE LOGITS
    eem
    1.68
    e
    1.58
    े
    1.34
    ein
    1.32
    eer
    1.32
    erde
    1.31
    a
    1.30
    ece
    1.27
    eh
    1.27
    eine
    1.25
    Activations Density 0.000%

    No Known Activations