© 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. 22-GEMMASCOPE-RES-131K
    7. 66347
    Prev
    Next
    INDEX
    Explanations

    PM emission

    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_22/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
     kemudian
    -1.72
    찼
    -1.46
    了什么
    -1.44
     where
    -1.39
     excepcional
    -1.33
     dilaporkan
    -1.30
     what
    -1.30
    DEPORTES
    -1.27
    CARACTERÍSTICAS
    -1.27
     addirittura
    -1.26
    POSITIVE LOGITS
     कीजिए
    1.32
    用
    1.25
     venit
    1.22
     отече
    1.20
     dolore
    1.18
     we
    1.16
    蔬菜
    1.15
    useNewUrlParser
    1.14
     世界
    1.12
    Jako
    1.12
    Activations Density 0.000%

    No Known Activations