© 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. 22-GEMMASCOPE-2-RES-16K
    7. 1084
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers and optimization

    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_22_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
    etc
    1.10
    sof
    1.05
     Etc
    1.01
    apollo
    1.01
     Toutes
    0.98
     وغيرها
    0.94
     :)
    0.94
     ;)
    0.91
    跟你
    0.91
     زیادی
    0.91
    POSITIVE LOGITS
     former
    1.56
     longtime
    1.47
     veteran
    1.43
     outgoing
    1.38
     fellow
    1.32
     seasoned
    1.31
     famed
    1.29
     proponents
    1.27
     critics
    1.22
     detractors
    1.22
    Activations Density 0.747%

    No Known Activations