© 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. 110569
    Prev
    Next
    INDEX
    Explanations

    introducing a topic

    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
    )
    -2.67
     
    -2.45
     esos
    -2.33
    l
    -1.91
    o
    -1.91
    [
    -1.88
     esas
    -1.87
     eve
    -1.84
     entire
    -1.84
    又被
    -1.84
    POSITIVE LOGITS
    衚
    2.89
    觧
    2.27
    鈇
    2.22
     leaſt
    2.19
    敺
    2.16
     från
    2.13
    趼
    2.11
    盉
    2.08
    ⃕
    2.03
    
    2.03
    Activations Density 0.056%

    No Known Activations