© 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. 74948
    Prev
    Next
    INDEX
    Explanations

    authors or reviewers

    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
     praticamente
    -1.46
    mismo
    -1.44
    㩒
    -1.33
     diariamente
    -1.30
     itſelf
    -1.28
     față
    -1.26
    之为
    -1.24
     publicités
    -1.23
    为例
    -1.23
    YEARS
    -1.23
    POSITIVE LOGITS
     to
    1.60
    {
    1.51
    тності
    1.45
     {
    1.42
     of
    1.37
     одной
    1.34
    １
    1.32
    osexuality
    1.30
    Also
    1.27
    insics
    1.27
    Activations Density 0.004%

    No Known Activations