© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7249
    Prev
    Next
    INDEX
    Explanations

    set out, set up, set a

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

    set by

    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
    Ј
    0.42
     সহিত
    0.41
    станов
    0.39
    sprites
    0.38
    మి
    0.37
    ധി
    0.37
    ઍ
    0.37
     নিকট
    0.37
    ಯ
    0.37
    িণ
    0.36
    POSITIVE LOGITS
     aside
    1.17
    aside
    1.03
     forth
    1.01
     ablaze
    0.97
    idaknya
    0.95
    uptools
    0.95
    TINGS
    0.94
     sail
    0.93
     alight
    0.90
    Aside
    0.90
    Activations Density 0.093%

    No Known Activations