© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 77
    Prev
    Next
    INDEX
    Explanations

    function definitions

    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
     Divulgação
    -1.37
     ошибка
    -1.37
     слишком
    -1.36
     вокруг
    -1.36
    大切に
    -1.34
    The
    -1.31
    +="
    -1.30
    也许
    -1.30
     braccia
    -1.29
     is
    -1.28
    POSITIVE LOGITS
     mikrofon
    1.34
     comenz
    1.25
     pól
    1.22
    出版年
    1.19
     lorsque
    1.18
     ilang
    1.12
     strukt
    1.11
     ↓,
    1.11
    関連項目
    1.10
    obacz
    1.09
    Activations Density 0.151%

    No Known Activations