© 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. 3186
    Prev
    Next
    INDEX
    Explanations

    is/are followed by -ing verbs

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

    alphabetical sequence

    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
     하기
    0.43
    是一個
    0.42
    是一个
    0.40
     کرنا
    0.37
     같은
    0.35
    하기
    0.33
     Showing
    0.33
     을
    0.33
     Britannia
    0.33
    うん
    0.33
    POSITIVE LOGITS
    asshi
    0.43
     मित्रता
    0.42
     puisqu
    0.41
    sembling
    0.40
     সেজন্য
    0.40
    cknowled
    0.39
    inerary
    0.39
     দুর্ভাগ্য
    0.39
     cuyos
    0.39
    /"+
    0.39
    Activations Density 0.019%

    No Known Activations