© 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. 10068
    Prev
    Next
    INDEX
    Explanations

    amp"}

    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
     in
    -2.31
     If
    -2.28
     While
    -2.22
     Since
    -2.17
     As
    -2.00
     at
    -1.94
     During
    -1.87
    {
    -1.85
     because
    -1.80
     after
    -1.79
    POSITIVE LOGITS
    粜
    2.33
     encantador
    2.13
     répand
    2.05
    ⵌ
    2.05
    喁
    2.05
    茈
    2.02
     atractivos
    2.02
     maravill
    2.00
    爌
    2.00
    绺
    1.99
    Activations Density 0.001%

    No Known Activations