© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43756
    Prev
    Next
    INDEX
    Explanations

    sequence marker

    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
     ausreich
    -1.61
    際には
    -1.48
    𖥧
    -1.46
    #,
    -1.44
    際は
    -1.38
    
    -1.37
     Waar
    -1.37
     появится
    -1.36
     medži
    -1.35
     }.
    -1.32
    POSITIVE LOGITS
    I
    1.84
    各种
    1.59
     various
    1.57
     которое
    1.54
    很多
    1.52
    That
    1.51
     который
    1.50
    鈰
    1.48
    何
    1.45
    为啥
    1.45
    Activations Density 0.032%

    No Known Activations