© 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. 104298
    Prev
    Next
    INDEX
    Explanations

    "successfully met all"

    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
     with
    -1.16
     that
    -1.14
     pomocą
    -1.13
     Entfer
    -1.11
     at
    -1.08
     without
    -1.08
    yaitu
    -1.08
     accesorios
    -1.06
     الشهر
    -1.05
    诟
    -1.05
    POSITIVE LOGITS
    則是
    1.23
    autre
    1.20
     ambienta
    1.16
     likewise
    1.16
    这两个
    1.16
    Zdrav
    1.15
    僥
    1.14
    ⢊
    1.13
    を選択
    1.12
    อีก
    1.12
    Activations Density 0.479%

    No Known Activations