© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 17885
    Prev
    Next
    INDEX
    Explanations

    hong Kong

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

    Hong Kong

    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
    }})^{
    0.40
    ემ
    0.39
    ಂಥ
    0.39
    भारी
    0.38
    ﮧ
    0.37
    StringUtils
    0.37
    भार
    0.36
    ensible
    0.36
    ophytes
    0.36
    agin
    0.36
    POSITIVE LOGITS
     Kong
    0.91
    kong
    0.89
     kong
    0.86
    Kong
    0.83
    콩
    0.63
     Hong
    0.51
     hong
    0.49
     KON
    0.49
     كون
    0.47
    磡
    0.46
    Activations Density 0.012%

    No Known Activations