© 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. 10-GEMMASCOPE-RES-131K
    7. 66052
    Prev
    Next
    INDEX
    Explanations

    `increasing number of`

    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_10/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
    
    -1.75
    但在
    -1.56
    最大の
    -1.53
    等我
    -1.52
    決して
    -1.50
    更に
    -1.48
     overflowing
    -1.46
     joue
    -1.45
     但
    -1.41
    但也
    -1.40
    POSITIVE LOGITS
     =
    1.64
     použí
    1.59
     believe
    1.55
     ideen
    1.52
     have
    1.50
     wako
    1.48
    骓
    1.45
    轵
    1.43
     października
    1.43
     répand
    1.41
    Activations Density 0.023%

    No Known Activations