© 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. 68833
    Prev
    Next
    INDEX
    Explanations

    causes and origins

    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
    مقدمه
    -1.40
    鉿
    -1.32
    تحميل
    -1.29
     analogous
    -1.26
    Definición
    -1.23
    硖
    -1.22
    띵
    -1.21
    getYear
    -1.21
     شما
    -1.20
    躂
    -1.19
    POSITIVE LOGITS
     why
    1.42
     which
    1.38
     and
    1.30
     pData
    1.18
     or
    1.18
     it
    1.18
    сі
    1.12
    fordshire
    1.11
     proč
    1.06
    я
    1.05
    Activations Density 0.119%

    No Known Activations