© 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. 61146
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
     Franse
    -1.62
     schild
    -1.52
     opět
    -1.45
     jezt
    -1.44
     betek
    -1.38
     eenen
    -1.36
    蹑
    -1.35
    岨
    -1.34
    Largeur
    -1.33
     offrent
    -1.32
    POSITIVE LOGITS
     because
    2.44
     when
    2.22
     and
    2.02
    er
    1.88
     after
    1.78
     in
    1.73
     as
    1.71
     only
    1.65
     people
    1.64
     until
    1.55
    Activations Density 0.019%

    No Known Activations