© 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. 130536
    Prev
    Next
    INDEX
    Explanations

    code documentation and definitions

    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
    鸱
    -1.52
     ?????
    -1.36
     ........
    -1.35
     .......
    -1.34
    etcode
    -1.34
    ようです
    -1.33
    背后
    -1.30
    背后的
    -1.29
     captiv
    -1.27
    Draco
    -1.27
    POSITIVE LOGITS
     where
    1.96
     which
    1.93
     only
    1.68
     this
    1.56
     actually
    1.55
     ensure
    1.46
     if
    1.41
     any
    1.40
     will
    1.37
     perhaps
    1.37
    Activations Density 0.046%

    No Known Activations