© 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. 75420
    Prev
    Next
    INDEX
    Explanations

    java annotations

    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
    是
    -1.80
     There
    -1.65
    KommentareTeilen
    -1.51
    Again
    -1.48
    ּוֹ
    -1.45
     Есть
    -1.44
    𐑂
    -1.44
     Since
    -1.44
    钲
    -1.43
     Undoubtedly
    -1.40
    POSITIVE LOGITS
    '
    1.51
     haupts
    1.45
     protège
    1.34
    摀
    1.33
     his
    1.32
    邶
    1.28
     小型
    1.27
    ANTY
    1.26
     ned
    1.23
     plutôt
    1.23
    Activations Density 0.001%

    No Known Activations