© 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. 65546
    Prev
    Next
    INDEX
    Explanations

    numbers and percentages

    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
     menik
    -1.61
     bahagia
    -1.55
     []:
    -1.54
    ❚
    -1.52
    hopped
    -1.51
     santiago
    -1.50
     abad
    -1.50
    hooting
    -1.50
     ambayo
    -1.48
    caping
    -1.46
    POSITIVE LOGITS
     Schluß
    1.80
     Sünde
    1.59
     only
    1.59
     größte
    1.57
     wahre
    1.53
    どうして
    1.52
     jahre
    1.52
     Bewußt
    1.52
     trabaja
    1.51
     wahren
    1.50
    Activations Density 0.035%

    No Known Activations