© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60015
    Prev
    Next
    INDEX
    Explanations

    hello world

    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
    </em>
    -1.50
    </b>
    -1.47
    これらの
    -1.42
     then
    -1.40
     such
    -1.38
     ‘’
    -1.36
     tych
    -1.27
     vorigen
    -1.23
     his
    -1.22
     dezelve
    -1.19
    POSITIVE LOGITS
    ︕
    1.50
    ✳
    1.41
    繋がり
    1.34
     göm
    1.30
    ☀
    1.27
    ادگی
    1.26
    StandardCharsets
    1.23
    ENOMEM
    1.23
    скую
    1.22
     rů
    1.21
    Activations Density 0.037%

    No Known Activations