© 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. 4698
    Prev
    Next
    INDEX
    Explanations

    first-trimester screening

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

    trillion, trimming, Trattoria, TRQ

    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
    ClFN
    0.48
    FBSDKApp
    0.35
    トー
    0.33
     ಏ
    0.33
    岦
    0.33
    鎿
    0.33
    尣
    0.33
    ᆺ
    0.32
    귄
    0.32
     euismod
    0.32
    POSITIVE LOGITS
    Tr
    3.64
     Tr
    3.50
    tr
    3.33
     TR
    3.31
     tr
    3.28
    TR
    3.28
     ट्र
    3.22
     ট্র
    3.02
     تر
    2.86
     Tristan
    2.86
    Activations Density 0.381%

    No Known Activations