© 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. 22-GEMMASCOPE-RES-131K
    7. 10
    Prev
    Next
    INDEX
    Explanations

    cryptographic keys and encoded strings

    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_22/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
     We
    -0.97
     appelez
    -0.96
    tdc
    -0.91
     découvrez
    -0.90
    
    -0.89
    anillo
    -0.88
     Grünen
    -0.87
    Suivez
    -0.87
     agences
    -0.86
    𝑭
    -0.85
    POSITIVE LOGITS
     MATTER
    0.98
    は
    0.97
    𓆜
    0.91
    ulatum
    0.91
    itively
    0.90
    ístico
    0.89
     ПО
    0.89
    êng
    0.88
    你这
    0.87
     envo
    0.85
    Activations Density 0.021%

    No Known Activations