© 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. 9420
    Prev
    Next
    INDEX
    Explanations

    mathematical and list separators

    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
    
    1.22
     Terc
    1.22
     でしょう
    1.20
     것입니다
    1.18
    かもしれません
    1.16
     Fifth
    1.08
    데요
    1.06
    ਖ
    1.06
    ʼ
    1.06
    かもしれませんが
    1.06
    POSITIVE LOGITS
    |
    4.06
     |
    3.90
    |(
    2.97
    .|
    2.91
    |.
    2.91
    |,
    2.86
     |.
    2.83
    ||
    2.79
    |[
    2.78
    )|
    2.78
    Activations Density 0.217%

    No Known Activations