© 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. 369
    Prev
    Next
    INDEX
    Explanations

    self-esteem and self-respect

    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
     Of
    -2.39
     the
    -2.20
     Then
    -2.11
     deemed
    -2.09
     They
    -2.09
     員
    -2.00
    ギフト
    -2.00
    ㈨
    -1.98
    もありました
    -1.97
    哢
    -1.94
    POSITIVE LOGITS
    ቍ
    1.97
    鱨
    1.95
    蠖
    1.95
    ዣ
    1.84
    訫
    1.80
    ’
    1.80
    {
    1.72
    ﹍﹍
    1.70
    ⚌
    1.70
    臜
    1.69
    Activations Density 0.003%

    No Known Activations