© 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. 57653
    Prev
    Next
    INDEX
    Explanations

    Jamaica and Jamaican entities

    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
    </h3>
    -3.58
    </sub>
    -3.00
    必要な
    -2.55
    好吗
    -2.47
     This
    -2.45
    他的
    -2.31
     midway
    -2.27
    还真是
    -2.27
     It
    -2.22
     But
    -2.22
    POSITIVE LOGITS
    姈
    2.98
    𞤢
    2.30
    ௅
    2.27
    The
    2.19
    das
    2.19
    (
    2.14
    鲞
    2.05
    the
    2.03
    ↵
    1.97
     nje
    1.95
    Activations Density 0.001%

    No Known Activations