© 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. 946
    Prev
    Next
    INDEX
    Explanations

    fiduciary relationships and official plans

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

    widely publicly available

    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
    十八
    0.46
    𓏸
    0.45
     Cái
    0.45
    ئین
    0.45
    ১৮
    0.41
    赐
    0.41
     государ
    0.40
     ঠাকুরের
    0.39
    彻底
    0.39
     Tao
    0.38
    POSITIVE LOGITS
    vý
    0.48
     ലി
    0.44
    <0xA6>
    0.43
    Вы
    0.43
    వి
    0.43
    ванный
    0.42
    Very
    0.42
     Вы
    0.41
    wght
    0.41
    whal
    0.41
    Activations Density 0.165%

    No Known Activations