© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 13373
    Prev
    Next
    INDEX
    Explanations

    mathematical theorems and laws

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

    mathematical theorems laws and logic

    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_31_width_262k_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
    🏤
    0.60
    
    0.58
     mieście
    0.54
     বাজার
    0.54
    ंचल
    0.52
    酒店
    0.52
    店铺
    0.51
     restoran
    0.51
     pagare
    0.50
    🏦
    0.50
    POSITIVE LOGITS
     theorem
    1.27
    Theorem
    1.16
     theorems
    1.13
     Theorem
    1.12
     Corollary
    1.07
     corollary
    1.05
    定理
    1.05
     teorema
    0.94
    Corollary
    0.90
     Theorems
    0.89
    Activations Density 0.014%

    No Known Activations