© 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. 1039
    Prev
    Next
    INDEX
    Explanations

    capable of being

    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
     to
    -2.39
     if
    -1.97
     Since
    -1.76
     are
    -1.74
     for
    -1.73
     many
    -1.68
     Many
    -1.66
     because
    -1.65
     this
    -1.64
     they
    -1.62
    POSITIVE LOGITS
    klare
    1.66
     légèrement
    1.56
    OTER
    1.49
    絝
    1.47
     suffisamment
    1.46
    
    1.39
    们的
    1.38
    Sumber
    1.38
    彇
    1.38
    ből
    1.37
    Activations Density 0.127%

    No Known Activations