© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 7324
    Prev
    Next
    INDEX
    Explanations

    theorem

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

    proving mathematical theorems

    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
     использование
    0.51
     használ
    0.45
    ◘
    0.45
    ใช้ง
    0.45
     use
    0.44
    rangian
    0.44
     gebruiken
    0.44
     використання
    0.44
    ➀
    0.44
     использовании
    0.43
    POSITIVE LOGITS
     theorem
    1.30
    theorem
    1.22
     Theorem
    1.10
    Theorem
    1.10
     theorems
    1.04
    newtheorem
    1.03
    定理
    1.00
     teorema
    0.99
     тео
    0.96
     Theorems
    0.94
    Activations Density 0.000%

    No Known Activations