© 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. 105134
    Prev
    Next
    INDEX
    Explanations

    beautifully followed by a descriptive word

    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
    _{
    -2.39
    鴞
    -2.22
    歘
    -1.98
     andet
    -1.94
    恫
    -1.91
     niyang
    -1.88
    骓
    -1.87
    杙
    -1.86
    럿
    -1.86
    嘏
    -1.84
    POSITIVE LOGITS
    [
    2.97
    i
    2.41
    This
    2.20
    ."
    2.19
    Please
    2.09
    Really
    2.09
    臯
    2.09
     the
    2.02
    </h5>
    2.02
    話は
    1.99
    Activations Density 0.003%

    No Known Activations