© 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. 376
    Prev
    Next
    INDEX
    Explanations

    as the name suggests

    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
    ’)
    -1.51
    borderSide
    -1.41
    ்
    -1.40
    琑
    -1.39
     mereka
    -1.36
     они
    -1.34
    า
    -1.33
    vanju
    -1.33
     specifically
    -1.30
     while
    -1.29
    POSITIVE LOGITS
     But
    1.59
     sorgfäl
    1.53
     แต่
    1.52
    Provides
    1.50
    provides
    1.48
    我们
    1.44
    IONA
    1.42
     We
    1.41
     anunció
    1.41
    盏
    1.41
    Activations Density 0.008%

    No Known Activations