© 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. 968
    Prev
    Next
    INDEX
    Explanations

    mathematical analysis and theorems

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

    algebraic structures

    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
     telehealth
    0.63
     personalidad
    0.62
    सायटी
    0.61
    өрү
    0.61
    뀔
    0.61
     amperage
    0.61
     foodservice
    0.61
    शिक्
    0.59
    kyverno
    0.59
    👏👏👏👏
    0.59
    POSITIVE LOGITS
     Theorem
    1.33
     Theorems
    1.30
    Theorem
    1.27
     theorems
    1.20
     abelian
    1.16
     Conjecture
    1.14
     extremal
    1.13
     cohom
    1.12
     asymptotics
    1.11
     conjectured
    1.10
    Activations Density 0.060%

    No Known Activations