© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 119464
    Prev
    Next
    INDEX
    Explanations

    functions and mathematical notation

    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
     wahre
    -1.34
     proceeding
    -1.34
    k
    -1.24
    d
    -1.23
     doesn
    -1.21
    发布时间
    -1.16
     natürliche
    -1.13
     促销
    -1.13
    款式
    -1.10
    M
    -1.10
    POSITIVE LOGITS
    </em>
    1.55
    <bos>
    1.33
    齪
    1.27
     Palabra
    1.26
    ſtra
    1.26
     */
    
    1.24
    ANDED
    1.24
    NSUserDefaults
    1.20
     muchos
    1.18
    惫
    1.18
    Activations Density 0.037%

    No Known Activations