© 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. 105667
    Prev
    Next
    INDEX
    Explanations

    scientific and mathematical concepts

    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
    </td>
    -1.48
     marié
    -1.20
    を利用
    -1.19
     verhält
    -1.17
    ”,
    -1.16
     It
    -1.15
     razões
    -1.13
    踌
    -1.11
     vnitř
    -1.11
    Its
    -1.11
    POSITIVE LOGITS
    Etimo
    1.38
     lyder
    1.35
     leider
    1.29
    ༑
    1.27
    eniem
    1.26
    앰
    1.26
    ischem
    1.25
     responsab
    1.25
    ktion
    1.22
    rauch
    1.22
    Activations Density 0.028%

    No Known Activations