© 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. 130326
    Prev
    Next
    INDEX
    Explanations

    require statement

    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
     people
    -1.29
     provide
    -1.29
     編
    -1.27
    centerTitle
    -1.23
     showcasing
    -1.20
     create
    -1.20
     in
    -1.16
    ﾗ
    -1.14
     relating
    -1.14
    äfts
    -1.13
    POSITIVE LOGITS
     cuarzo
    1.25
    ㍑
    1.25
     démarrer
    1.24
     lille
    1.22
     gewisse
    1.21
    延伸閱讀
    1.20
     kategor
    1.20
     segü
    1.17
    anmar
    1.16
     kome
    1.15
    Activations Density 0.039%

    No Known Activations