© 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. 2590
    Prev
    Next
    INDEX
    Explanations

    interest added to balance

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

    predicting sequential elements

    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
     حوالي
    0.47
     Approximate
    0.42
     tér
    0.41
    蛔
    0.40
     úpl
    0.39
    Ą
    0.39
     শোনা
    0.39
     ثلاثة
    0.39
    钨
    0.39
     দিয়েছেন
    0.38
    POSITIVE LOGITS
     cumul
    0.60
     periód
    0.57
     cumulative
    0.56
     periodically
    0.55
     sums
    0.54
     continually
    0.54
     successively
    0.54
     successivo
    0.54
     계속
    0.52
     snowball
    0.52
    Activations Density 0.001%

    No Known Activations