© 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. 99785
    Prev
    Next
    INDEX
    Explanations

    words starting with xt

    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
    ↵↵
    -2.19
    ㈥
    -2.11
     varied
    -2.09
    但
    -2.05
    felpa
    -2.05
    
    -2.00
    
    -1.98
    
    -1.98
    名の
    -1.97
    但不
    -1.93
    POSITIVE LOGITS
    ский
    2.64
    寕
    2.48
    螽
    2.45
    Xtra
    2.30
    /"
    2.30
    isation
    2.27
    ですので
    2.25
    ifikant
    2.25
     hablaba
    2.25
    ︲
    2.20
    Activations Density 0.001%

    No Known Activations