© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 789
    Prev
    Next
    INDEX
    Explanations

    ammonium, math, Ammonites

    np_acts-logits-general · gemini-2.5-flash-lite

    asynchronous operations and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_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
    ㄒ
    0.43
     दिलाने
    0.42
    旯
    0.42
     ойноо
    0.42
    🐯
    0.42
    🛖
    0.41
     imagining
    0.40
    🙍
    0.40
     ойнотуу
    0.40
    बाड़ी
    0.40
    POSITIVE LOGITS
     AMS
    1.05
    amssymb
    1.03
    AMS
    0.92
    amsfonts
    0.92
    amsmath
    0.89
     Ammon
    0.79
     ammonium
    0.78
     Ammonium
    0.76
    symbol
    0.75
    ams
    0.74
    Activations Density 0.005%

    No Known Activations