© 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. 75017
    Prev
    Next
    INDEX
    Explanations

    Microsoft Surface or greetings

    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
    他还
    -1.69
    ations
    -1.62
     isn
    -1.61
    认真的
    -1.59
     فقط
    -1.59
     ‐
    -1.58
     получила
    -1.54
     souligne
    -1.53
    ﹎
    -1.52
     mishap
    -1.51
    POSITIVE LOGITS
    ğından
    1.60
    葯
    1.54
     elektri
    1.46
    ͉
    1.41
    </h2>
    1.41
    </sup>
    1.38
    ramientas
    1.38
    ꦫ
    1.38
     such
    1.37
    迓
    1.37
    Activations Density 0.000%

    No Known Activations