© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 97900
    Prev
    Next
    INDEX
    Explanations

    prove you wrong

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     proof
    -1.09
     prueba
    -1.03
     prova
    -0.93
    魉
    -0.89
     поверх
    -0.86
     получить
    -0.85
     proofs
    -0.84
    PO
    -0.84
     applaud
    -0.81
     is
    -0.81
    POSITIVE LOGITS
     wrong
    1.45
     conclusively
    1.38
     definitively
    1.16
     claims
    1.01
     theorems
    0.99
     pudding
    0.99
     estatu
    0.97
     beyond
    0.96
     WRONG
    0.94
     mathematically
    0.94
    Activations Density 0.028%

    No Known Activations