© 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. 69078
    Prev
    Next
    INDEX
    Explanations

    code documentation snippets

    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
    ۷
    -1.88
     herre
    -1.82
    馊
    -1.80
     ſever
    -1.80
     bords
    -1.80
    鲧
    -1.79
     fourrure
    -1.78
     engelsk
    -1.75
    ofus
    -1.74
    ۸
    -1.74
    POSITIVE LOGITS
    ↵
    2.63
     to
    2.59
    {
    2.55
     you
    2.05
     only
    1.91
     this
    1.91
     now
    1.89
     (!__
    1.63
     few
    1.61
     really
    1.59
    Activations Density 0.034%

    No Known Activations