© 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. 123567
    Prev
    Next
    INDEX
    Explanations

    artificial neural network

    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
     grandeza
    -1.29
     permettant
    -1.25
    馀
    -1.23
    
    -1.22
     preciosa
    -1.18
     réserver
    -1.15
     verbe
    -1.13
    亩
    -1.12
    Moreover
    -1.12
    iously
    -1.12
    POSITIVE LOGITS
    ො
    1.28
     also
    1.26
    ,
    1.24
    台南
    1.23
    Где
    1.20
    莘
    1.18
     tiež
    1.16
    akterysty
    1.16
    Bước
    1.15
    먼
    1.14
    Activations Density 0.031%

    No Known Activations