© 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. 10-GEMMASCOPE-RES-131K
    4. 42766
    Prev
    Next
    INDEX
    Explanations

    choices, options, lists

    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
    ↵↵
    -1.89
     you
    -1.72
     i
    -1.71
        
    -1.58
     he
    -1.42
     determines
    -1.39
     “
    -1.38
    1
    -1.37
     tells
    -1.34
     influence
    -1.33
    POSITIVE LOGITS
    澌
    1.77
    itées
    1.65
     uska
    1.64
    沨
    1.64
    choices
    1.60
    <bos>
    1.59
    aneity
    1.57
    鈇
    1.56
    𞤢
    1.55
    赑
    1.55
    Activations Density 0.005%

    No Known Activations