© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 340
    Prev
    Next
    INDEX
    Explanations

    Chinese names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    岬
    1.01
     Donegal
    0.90
     --
    0.87
     labores
    0.83
     possibilit
    0.82
    怙
    0.79
     Maltese
    0.78
     —
    0.75
    €“
    0.74
     Slov
    0.73
    POSITIVE LOGITS
     Zhao
    2.20
     Qian
    2.17
     Xiao
    2.14
     Jiang
    2.14
     Zheng
    2.13
     Xie
    2.13
     Guangdong
    2.12
     Xiang
    2.12
     Qin
    2.11
     Fei
    2.09
    Activations Density 1.109%

    No Known Activations