© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 13497
    Prev
    Next
    INDEX
    Explanations

    .

    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
     tho
    -1.13
     tha
    -1.00
    ande
    -0.98
     ef
    -0.94
     particular
    -0.94
     ans
    -0.94
     tb
    -0.93
    protoimpl
    -0.90
     him
    -0.89
    keletal
    -0.88
    POSITIVE LOGITS
    Dzień
    1.31
    Więcej
    1.13
    Zapraszamy
    1.06
    ݁
    1.05
     réglementation
    1.05
    Veja
    1.04
    忪
    1.03
    Może
    1.02
    Literat
    1.02
    Nuestro
    1.00
    Activations Density 0.018%

    No Known Activations