© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14404
    Prev
    Next
    INDEX
    Explanations

    $ followed by M

    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
     the
    -1.68
     comenzaron
    -1.55
     empezaron
    -1.48
                
    -1.45
     Wartawan
    -1.36
                    
    -1.30
     only
    -1.28
     here
    -1.27
               
    -1.27
     either
    -1.27
    POSITIVE LOGITS
    ↵↵
    1.81
     contenta
    1.40
     شیپور
    1.39
     contento
    1.32
     cristian
    1.29
    降临
    1.29
     industria
    1.27
    ザイン
    1.26
    ».
    1.25
     insum
    1.25
    Activations Density 0.000%

    No Known Activations