© 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. 2740
    Prev
    Next
    INDEX
    Explanations

    list items

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

    topics after list items

    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
     επέ
    0.31
    秇
    0.31
     Максим
    0.30
     ойнотуу
    0.30
    }^{*}=
    0.29
    喑
    0.29
     senc
    0.29
     hava
    0.29
     MeOH
    0.28
     رضا
    0.28
    POSITIVE LOGITS
     impenetr
    0.35
     decidedly
    0.32
     haired
    0.32
     ܀
    0.30
    ictionaries
    0.30
     intravenous
    0.29
     abbreviation
    0.29
     abbreviations
    0.29
     types
    0.29
     intestine
    0.29
    Activations Density 0.116%

    No Known Activations