© 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-65K
    7. 2828
    Prev
    Next
    INDEX
    Explanations

    code structures and regex

    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_65k_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
     Matt
    0.86
     demo
    0.78
     fic
    0.77
     rom
    0.77
    ,...
    0.76
     Brit
    0.76
    *,
    0.76
     ten
    0.74
    ​,
    0.74
     colonial
    0.72
    POSITIVE LOGITS
    下标
    1.16
    括号
    1.00
    序号
    0.98
    ញ
    0.96
    ACIONES
    0.91
    しく
    0.91
    اہد
    0.90
    匕
    0.89
    िएशन
    0.89
    Substitute
    0.88
    Activations Density 0.076%

    No Known Activations